Search Results for author: Alexander Wong

Found 210 papers, 37 papers with code

Where’s the Question? A Multi-channel Deep Convolutional Neural Network for Question Identification in Textual Data

no code implementations EMNLP (ClinicalNLP) 2020 George Michalopoulos, Helen Chen, Alexander Wong

The gold standard in clinical data capturing is achieved via “expert-review”, where clinicians can have a dialogue with a domain expert (reviewers) and ask them questions about data entry rules.

Sentence

Optimizing Synthetic Correlated Diffusion Imaging for Breast Cancer Tumour Delineation

no code implementations13 May 2024 Chi-en Amy Tai, Alexander Wong

Breast cancer is a significant cause of death from cancer in women globally, highlighting the need for improved diagnostic imaging to enhance patient outcomes.

NutritionVerse-Direct: Exploring Deep Neural Networks for Multitask Nutrition Prediction from Food Images

no code implementations13 May 2024 Matthew Keller, Chi-en Amy Tai, Yuhao Chen, Pengcheng Xi, Alexander Wong

Many aging individuals encounter challenges in effectively tracking their dietary intake, exacerbating their susceptibility to nutrition-related health complications.

Nutrition

Using Multiparametric MRI with Optimized Synthetic Correlated Diffusion Imaging to Enhance Breast Cancer Pathologic Complete Response Prediction

no code implementations13 May 2024 Chi-en Amy Tai, Alexander Wong

In 2020, 685, 000 deaths across the world were attributed to breast cancer, underscoring the critical need for innovative and effective breast cancer treatment.

In The Wild Ellipse Parameter Estimation for Circular Dining Plates and Bowls

no code implementations12 May 2024 Akil Pathiranage, Chris Czarnecki, Yuhao Chen, Pengcheng Xi, Linlin Xu, Alexander Wong

Ellipse estimation is an important topic in food image processing because it can be leveraged to parameterize plates and bowls, which in turn can be used to estimate camera view angles and food portion sizes.

Semantic Segmentation

Domain-Guided Masked Autoencoders for Unique Player Identification

no code implementations17 Mar 2024 Bavesh Balaji, Jerrin Bright, Sirisha Rambhatla, Yuhao Chen, Alexander Wong, John Zelek, David A Clausi

We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification.

Sports Analytics

Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound

no code implementations12 Mar 2024 Blake VanBerlo, Alexander Wong, Jesse Hoey, Robert Arntfield

Guidelines for practitioners were synthesized based on the results, such as the merit of IVPP with task-specific hyperparameters, and the improved performance of contrastive methods for ultrasound compared to non-contrastive counterparts.

Contrastive Learning Self-Supervised Learning

Step length measurement in the wild using FMCW radar

no code implementations3 Jan 2024 Parthipan Siva, Alexander Wong, Patricia Hewston, George Ioannidis, Dr. Jonathan Adachi, Dr. Alexander Rabinovich, Andrea Lee, Alexandra Papaioannou

To address this gap, a radar-based step length measurement system for the home is proposed based on detection and tracking using radar point cloud, followed by Doppler speed profiling of the torso to obtain step lengths in the home.

Privacy Preserving

DVQI: A Multi-task, Hardware-integrated Artificial Intelligence System for Automated Visual Inspection in Electronics Manufacturing

no code implementations14 Dec 2023 Audrey Chung, Francis Li, Jeremy Ward, Andrew Hryniowski, Alexander Wong

In this paper, we present the DarwinAI Visual Quality Inspection (DVQI) system, a hardware-integration artificial intelligence system for the automated inspection of printed circuit board assembly defects in an electronics manufacturing environment.

NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation

no code implementations11 Dec 2023 Saeejith Nair, Chi-en Amy Tai, Yuhao Chen, Alexander Wong

As the largest open-source synthetic food dataset, NV-Synth highlights the value of physics-based simulations for enabling scalable and controllable generation of diverse photorealistic meal images to overcome data limitations and drive advancements in automated dietary assessment using computer vision.

DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence

no code implementations8 Dec 2023 Saeejith Nair, Mohammad Javad Shafiee, Alexander Wong

We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents.

Evolutionary Algorithms reinforcement-learning

FoodFusion: A Latent Diffusion Model for Realistic Food Image Generation

no code implementations6 Dec 2023 Olivia Markham, Yuhao Chen, Chi-en Amy Tai, Alexander Wong

To address these limitations, we introduce FoodFusion, a Latent Diffusion model engineered specifically for the faithful synthesis of realistic food images from textual descriptions.

Image Generation

Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion

no code implementations30 Nov 2023 Aditya Sridhar, Chi-en Amy Tai, Hayden Gunraj, Yuhao Chen, Alexander Wong

In Canada, prostate cancer is the most common form of cancer in men and accounted for 20% of new cancer cases for this demographic in 2022.

COVIDx CXR-4: An Expanded Multi-Institutional Open-Source Benchmark Dataset for Chest X-ray Image-Based Computer-Aided COVID-19 Diagnostics

no code implementations29 Nov 2023 Yifan Wu, Hayden Gunraj, Chi-en Amy Tai, Alexander Wong

The global ramifications of the COVID-19 pandemic remain significant, exerting persistent pressure on nations even three years after its initial outbreak.

NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation

no code implementations20 Nov 2023 Chi-en Amy Tai, Saeejith Nair, Olivia Markham, Matthew Keller, Yifan Wu, Yuhao Chen, Alexander Wong

Dietary intake estimation plays a crucial role in understanding the nutritional habits of individuals and populations, aiding in the prevention and management of diet-related health issues.

Management

Cancer-Net PCa-Data: An Open-Source Benchmark Dataset for Prostate Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data

no code implementations20 Nov 2023 Hayden Gunraj, Chi-en Amy Tai, Alexander Wong

The recent introduction of synthetic correlated diffusion (CDI$^s$) imaging has demonstrated significant potential in the realm of clinical decision support for prostate cancer (PCa).

On Calibration of Modern Quantized Efficient Neural Networks

no code implementations25 Sep 2023 Joey Kuang, Alexander Wong

We explore calibration properties at various precisions for three architectures: ShuffleNetv2, GhostNet-VGG, and MobileOne; and two datasets: CIFAR-100 and PathMNIST.

Quantization

NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields

no code implementations25 Sep 2023 Saeejith Nair, Yuhao Chen, Mohammad Javad Shafiee, Alexander Wong

Thus, there is a need to dynamically optimize the neural network component of NeRFs to achieve a balance between computational complexity and specific targets for synthesis quality.

Neural Architecture Search Novel View Synthesis +1

GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks

no code implementations24 Sep 2023 Stone Yun, Alexander Wong

Graph Hypernetworks (GHN) can predict the parameters of varying unseen CNN architectures with surprisingly good accuracy at a fraction of the cost of iterative optimization.

Quantization

NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches

no code implementations14 Sep 2023 Chi-en Amy Tai, Matthew Keller, Saeejith Nair, Yuhao Chen, Yifan Wu, Olivia Markham, Krish Parmar, Pengcheng Xi, Heather Keller, Sharon Kirkpatrick, Alexander Wong

Recent work has focused on using computer vision and machine learning to automatically estimate dietary intake from food images, but the lack of comprehensive datasets with diverse viewpoints, modalities and food annotations hinders the accuracy and realism of such methods.

A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images

no code implementations5 Sep 2023 Blake VanBerlo, Jesse Hoey, Alexander Wong

Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data.

Clinical Knowledge Self-Supervised Learning +1

Self-Supervised Pretraining Improves Performance and Inference Efficiency in Multiple Lung Ultrasound Interpretation Tasks

no code implementations5 Sep 2023 Blake VanBerlo, Brian Li, Jesse Hoey, Alexander Wong

In this study, we investigated whether self-supervised pretraining could produce a neural network feature extractor applicable to multiple classification tasks in B-mode lung ultrasound analysis.

TurboViT: Generating Fast Vision Transformers via Generative Architecture Search

no code implementations22 Aug 2023 Alexander Wong, Saad Abbasi, Saeejith Nair

In this study, we explore the generation of fast vision transformer architecture designs via generative architecture search (GAS) to achieve a strong balance between accuracy and architectural and computational efficiency.

Computational Efficiency

GoalieNet: A Multi-Stage Network for Joint Goalie, Equipment, and Net Pose Estimation in Ice Hockey

no code implementations28 Jun 2023 Marjan Shahi, David Clausi, Alexander Wong

In the field of computer vision-driven ice hockey analytics, one of the most challenging and least studied tasks is goalie pose estimation.

Pose Estimation

Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis

no code implementations16 Jun 2023 Andre Hryniowski, Alexander Wong

In addition, we demonstrate that results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance compared to an extensive parameter search.

Transferring Knowledge for Food Image Segmentation using Transformers and Convolutions

no code implementations15 Jun 2023 Grant Sinha, Krish Parmar, Hilda Azimi, Amy Tai, Yuhao Chen, Alexander Wong, Pengcheng Xi

To address these issues, two models are trained and compared, one based on convolutional neural networks and the other on Bidirectional Encoder representation for Image Transformers (BEiT).

Image Segmentation Segmentation +1

Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability

no code implementations14 Jun 2023 E. Zhixuan Zeng, Hayden Gunraj, Sheldon Fernandez, Alexander Wong

In this work, we explore the use of this higher-level interpretation of a deep neural network's behaviour to allows us to "explain the explainability" for actionable insights.

Explainable Artificial Intelligence (XAI)

DeepfakeArt Challenge: A Benchmark Dataset for Generative AI Art Forgery and Data Poisoning Detection

1 code implementation2 Jun 2023 Hossein Aboutalebi, Dayou Mao, Carol Xu, Alexander Wong

Motivated to address these key concerns to encourage responsible generative AI, we introduce the DeepfakeArt Challenge, a large-scale challenge benchmark dataset designed specifically to aid in the building of machine learning algorithms for generative AI art forgery and data poisoning detection.

Data Poisoning

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge

no code implementations21 Apr 2023 Alexander Wong, Yifan Wu, Saad Abbasi, Saeejith Nair, Yuhao Chen, Mohammad Javad Shafiee

As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments.

Multi-Task Learning Robotic Grasping

A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data

1 code implementation12 Apr 2023 Chi-en Amy Tai, Hayden Gunraj, Alexander Wong

Recently, a new form of magnetic resonance imaging (MRI) called synthetic correlated diffusion (CDI$^s$) imaging was introduced and showed considerable promise for clinical decision support for cancers such as prostate cancer when compared to current gold-standard MRI techniques.

NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation

no code implementations12 Apr 2023 Chi-en Amy Tai, Matthew Keller, Mattie Kerrigan, Yuhao Chen, Saeejith Nair, Pengcheng Xi, Alexander Wong

Unlike existing datasets, a collection of 3D models with nutritional information allow for view synthesis to create an infinite number of 2D images for any given viewpoint/camera angle along with the associated nutritional information.

Nutrition

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

no code implementations12 Apr 2023 Chi-en Amy Tai, Jason Li, Sriram Kumar, Saeejith Nair, Yuhao Chen, Pengcheng Xi, Alexander Wong

With the growth in capabilities of generative models, there has been growing interest in using photo-realistic renders of common 3D food items to improve downstream tasks such as food printing, nutrition prediction, or management of food wastage.

Management Nutrition

Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging

1 code implementation12 Apr 2023 Chi-en Amy Tai, Hayden Gunraj, Alexander Wong

The prevalence of breast cancer continues to grow, affecting about 300, 000 females in the United States in 2023.

ShapeShift: Superquadric-based Object Pose Estimation for Robotic Grasping

no code implementations10 Apr 2023 E. Zhixuan Zeng, Yuhao Chen, Alexander Wong

To address these challenges, this paper proposes ShapeShift, a superquadric-based framework for object pose estimation that predicts the object's pose relative to a primitive shape which is fitted to the object.

Object Pose Estimation +1

Exploring the Utility of Self-Supervised Pretraining Strategies for the Detection of Absent Lung Sliding in M-Mode Lung Ultrasound

no code implementations5 Apr 2023 Blake VanBerlo, Brian Li, Alexander Wong, Jesse Hoey, Robert Arntfield

This study investigates the utility of self-supervised pretraining prior to conducting supervised fine-tuning for the downstream task of lung sliding classification in M-mode lung ultrasound images.

Data Augmentation

Recurrence With Correlation Network for Medical Image Registration

1 code implementation5 Feb 2023 Vignesh Sivan, Teodora Vujovic, Raj Ranabhat, Alexander Wong, Stewart McLachlin, Michael Hardisty

We present Recurrence with Correlation Network (RWCNet), a medical image registration network with multi-scale features and a cost volume layer.

Image Registration Medical Image Registration

PCBDet: An Efficient Deep Neural Network Object Detection Architecture for Automatic PCB Component Detection on the Edge

no code implementations23 Jan 2023 Brian Li, Steven Palayew, Francis Li, Saad Abbasi, Saeejith Nair, Alexander Wong

There can be numerous electronic components on a given PCB, making the task of visual inspection to detect defects very time-consuming and prone to error, especially at scale.

Edge-computing object-detection +1

COVID-Net USPro: An Open-Source Explainable Few-Shot Deep Prototypical Network to Monitor and Detect COVID-19 Infection from Point-of-Care Ultrasound Images

no code implementations4 Jan 2023 Jessy Song, Ashkan Ebadi, Adrian Florea, Pengcheng Xi, Stéphane Tremblay, Alexander Wong

As the Coronavirus Disease 2019 (COVID-19) continues to impact many aspects of life and the global healthcare systems, the adoption of rapid and effective screening methods to prevent further spread of the virus and lessen the burden on healthcare providers is a necessity.

High-Throughput, High-Performance Deep Learning-Driven Light Guide Plate Surface Visual Quality Inspection Tailored for Real-World Manufacturing Environments

no code implementations20 Dec 2022 Carol Xu, Mahmoud Famouri, Gautam Bathla, Mohammad Javad Shafiee, Alexander Wong

As such, the proposed deep learning-driven workflow, integrated with the aforementioned LightDefectNet neural network, is highly suited for high-throughput, high-performance light plate surface VQI within real-world manufacturing environments.

Defect Detection Edge-computing +1

Plankton-FL: Exploration of Federated Learning for Privacy-Preserving Training of Deep Neural Networks for Phytoplankton Classification

no code implementations18 Dec 2022 Daniel Zhang, Vikram Voleti, Alexander Wong, Jason Deglint

In this study, we explore the feasibility of leveraging federated learning for privacy-preserving training of deep neural networks for phytoplankton classification.

Federated Learning Privacy Preserving

A Trustworthy Framework for Medical Image Analysis with Deep Learning

no code implementations6 Dec 2022 Kai Ma, Siyuan He, Pengcheng Xi, Ashkan Ebadi, Stéphane Tremblay, Alexander Wong

Computer vision and machine learning are playing an increasingly important role in computer-assisted diagnosis; however, the application of deep learning to medical imaging has challenges in data availability and data imbalance, and it is especially important that models for medical imaging are built to be trustworthy.

COVID-Net Assistant: A Deep Learning-Driven Virtual Assistant for COVID-19 Symptom Prediction and Recommendation

no code implementations22 Nov 2022 Pengyuan Shi, Yuetong Wang, Saad Abbasi, Alexander Wong

As the COVID-19 pandemic continues to put a significant burden on healthcare systems worldwide, there has been growing interest in finding inexpensive symptom pre-screening and recommendation methods to assist in efficiently using available medical resources such as PCR tests.

A Fair Loss Function for Network Pruning

no code implementations18 Nov 2022 Robbie Meyer, Alexander Wong

Model pruning can enable the deployment of neural networks in environments with resource constraints.

Fairness Lesion Classification +2

Enhancing Clinical Support for Breast Cancer with Deep Learning Models using Synthetic Correlated Diffusion Imaging

1 code implementation10 Nov 2022 Chi-en Amy Tai, Hayden Gunraj, Nedim Hodzic, Nic Flanagan, Ali Sabri, Alexander Wong

Breast cancer is the second most common type of cancer in women in Canada and the United States, representing over 25\% of all new female cancer cases.

MMRNet: Improving Reliability for Multimodal Object Detection and Segmentation for Bin Picking via Multimodal Redundancy

no code implementations19 Oct 2022 Yuhao Chen, Hayden Gunraj, E. Zhixuan Zeng, Robbie Meyer, Maximilian Gilles, Alexander Wong

We also demonstrate that our MC score is a more reliability indicator for outputs during inference time compared to the model generated confidence scores that are often over-confident.

Ensemble Learning object-detection +1

GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks

no code implementations26 Aug 2022 Stone Yun, Alexander Wong

We conduct the first-ever study exploring the use of graph hypernetworks for predicting parameters of unseen quantized CNN architectures.

Adversarial Robustness Parameter Prediction +1

Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture for the Edge via Double-Condensing Attention Condensers

no code implementations15 Aug 2022 Alexander Wong, Mohammad Javad Shafiee, Saad Abbasi, Saeejith Nair, Mahmoud Famouri

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge.

Efficient Neural Network

AI-Powered Non-Contact In-Home Gait Monitoring and Activity Recognition System Based on mm-Wave FMCW Radar and Cloud Computing

no code implementations11 Aug 2022 Hajar Abedi, Ahmad Ansariyan, Plinio P Morita, Alexander Wong, Jennifer Boger, George Shaker

In this paper, leveraging AI, cloud computing and radar technology, we create intelligent sensing that enables smarter applications to improve people's daily lives.

Activity Recognition Cloud Computing

MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis

no code implementations8 Aug 2022 Maximilian Gilles, Yuhao Chen, Tim Robin Winter, E. Zhixuan Zeng, Alexander Wong

Autonomous bin picking poses significant challenges to vision-driven robotic systems given the complexity of the problem, ranging from various sensor modalities, to highly entangled object layouts, to diverse item properties and gripper types.

Keypoint Detection Object +2

Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms

no code implementations3 Aug 2022 Nitpreet Bamra, Vikram Voleti, Alexander Wong, Jason Deglint

Thus, this work demonstrates the ability of GANs to create large synthetic datasets of phytoplankton from small training datasets, accomplishing a key step towards sustainable systematic monitoring of harmful algal blooms.

Management

Towards Trustworthy Healthcare AI: Attention-Based Feature Learning for COVID-19 Screening With Chest Radiography

no code implementations19 Jul 2022 Kai Ma, Pengcheng Xi, Karim Habashy, Ashkan Ebadi, Stéphane Tremblay, Alexander Wong

In this study, we propose a feature learning approach using Vision Transformers, which use an attention-based mechanism, and examine the representation learning capability of Transformers as a new backbone architecture for medical imaging.

Representation Learning

COVIDx CXR-3: A Large-Scale, Open-Source Benchmark Dataset of Chest X-ray Images for Computer-Aided COVID-19 Diagnostics

no code implementations8 Jun 2022 Maya Pavlova, Tia Tuinstra, Hossein Aboutalebi, Andy Zhao, Hayden Gunraj, Alexander Wong

After more than two years since the beginning of the COVID-19 pandemic, the pressure of this crisis continues to devastate globally.

MAPLE-X: Latency Prediction with Explicit Microprocessor Prior Knowledge

no code implementations25 May 2022 Saad Abbasi, Alexander Wong, Mohammad Javad Shafiee

Deep neural network (DNN) latency characterization is a time-consuming process and adds significant cost to Neural Architecture Search (NAS) processes when searching for efficient convolutional neural networks for embedded vision applications.

Neural Architecture Search

COVID-Net UV: An End-to-End Spatio-Temporal Deep Neural Network Architecture for Automated Diagnosis of COVID-19 Infection from Ultrasound Videos

no code implementations18 May 2022 Hilda Azimi, Ashkan Ebadi, Jessy Song, Pengcheng Xi, Alexander Wong

Besides vaccination, as an effective way to mitigate the further spread of COVID-19, fast and accurate screening of individuals to test for the disease is yet necessary to ensure public health safety.

COVID-Net US-X: Enhanced Deep Neural Network for Detection of COVID-19 Patient Cases from Convex Ultrasound Imaging Through Extended Linear-Convex Ultrasound Augmentation Learning

1 code implementation29 Apr 2022 E. Zhixuan Zeng, Adrian Florea, Alexander Wong

As the global population continues to face significant negative impact by the on-going COVID-19 pandemic, there has been an increasing usage of point-of-care ultrasound (POCUS) imaging as a low-cost and effective imaging modality of choice in the COVID-19 clinical workflow.

Data Augmentation

MAPLE-Edge: A Runtime Latency Predictor for Edge Devices

no code implementations27 Apr 2022 Saeejith Nair, Saad Abbasi, Alexander Wong, Mohammad Javad Shafiee

Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications.

Efficient Neural Network Neural Architecture Search

LightDefectNet: A Highly Compact Deep Anti-Aliased Attention Condenser Neural Network Architecture for Light Guide Plate Surface Defect Detection

no code implementations25 Apr 2022 Carol Xu, Mahmoud Famouri, Gautam Bathla, Mohammad Javad Shafiee, Alexander Wong

Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays.

Defect Detection

COVID-Net Biochem: An Explainability-driven Framework to Building Machine Learning Models for Predicting Survival and Kidney Injury of COVID-19 Patients from Clinical and Biochemistry Data

1 code implementation24 Apr 2022 Hossein Aboutalebi, Maya Pavlova, Mohammad Javad Shafiee, Adrian Florea, Andrew Hryniowski, Alexander Wong

Since the World Health Organization declared COVID-19 a pandemic in 2020, the global community has faced ongoing challenges in controlling and mitigating the transmission of the SARS-CoV-2 virus, as well as its evolving subvariants and recombinants.

Decision Making Injury Prediction

ICDBigBird: A Contextual Embedding Model for ICD Code Classification

no code implementations BioNLP (ACL) 2022 George Michalopoulos, Michal Malyska, Nicola Sahar, Alexander Wong, Helen Chen

The International Classification of Diseases (ICD) system is the international standard for classifying diseases and procedures during a healthcare encounter and is widely used for healthcare reporting and management purposes.

Classification Code Classification +2

FenceNet: Fine-grained Footwork Recognition in Fencing

no code implementations20 Apr 2022 Kevin Zhu, Alexander Wong, John McPhee

FenceNet takes 2D pose data as input and classifies actions using a skeleton-based action recognition approach that incorporates temporal convolutional networks to capture temporal information.

Action Recognition Feature Engineering +1

Improving Classification Model Performance on Chest X-Rays through Lung Segmentation

no code implementations22 Feb 2022 Hilda Azimi, Jianxing Zhang, Pengcheng Xi, Hala Asad, Ashkan Ebadi, Stephane Tremblay, Alexander Wong

Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.

Classification Segmentation

Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning

1 code implementation22 Jan 2022 Brennan Gebotys, Alexander Wong, David A. Clausi

Natural policy gradient methods are popular reinforcement learning methods that improve the stability of policy gradient methods by utilizing second-order approximations to precondition the gradient with the inverse of the Fisher-information matrix.

Policy Gradient Methods reinforcement-learning +1

MetaGraspNet_v0: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis

1 code implementation29 Dec 2021 Yuhao Chen, E. Zhixuan Zeng, Maximilian Gilles, Alexander Wong

We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance in a manner that is more appropriate for robotic grasp applications compared to existing general-purpose performance metrics.

Object object-detection +3

MAPLE: Microprocessor A Priori for Latency Estimation

no code implementations30 Nov 2021 Saad Abbasi, Alexander Wong, Mohammad Javad Shafiee

Through this quantitative strategy as the hardware descriptor, MAPLE can generalize to new hardware via a few shot adaptation strategy where with as few as 3 samples it exhibits a 6% improvement over state-of-the-art methods requiring as much as 10 samples.

Domain Adaptation Neural Architecture Search +1

M2A: Motion Aware Attention for Accurate Video Action Recognition

1 code implementation18 Nov 2021 Brennan Gebotys, Alexander Wong, David A. Clausi

We further compared the performance of M2A with other state-of-the-art motion and attention mechanisms on the Something-Something V1 video action recognition benchmark.

Action Recognition Temporal Action Localization +1

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

1 code implementation16 Nov 2021 William McNally, Kanav Vats, Alexander Wong, John McPhee

In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process.

Keypoint Estimation Pose Estimation

COVID-Net MLSys: Designing COVID-Net for the Clinical Workflow

no code implementations14 Sep 2021 Audrey G. Chung, Maya Pavlova, Hayden Gunraj, Naomi Terhljan, Alexander MacLean, Hossein Aboutalebi, Siddharth Surana, Andy Zhao, Saad Abbasi, Alexander Wong

As the COVID-19 pandemic continues to devastate globally, one promising field of research is machine learning-driven computer vision to streamline various parts of the COVID-19 clinical workflow.

BIG-bench Machine Learning

COVID-Net Clinical ICU: Enhanced Prediction of ICU Admission for COVID-19 Patients via Explainability and Trust Quantification

no code implementations14 Sep 2021 Audrey Chung, Mahmoud Famouri, Andrew Hryniowski, Alexander Wong

The COVID-19 pandemic continues to have a devastating global impact, and has placed a tremendous burden on struggling healthcare systems around the world.

Decision Making

Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning

no code implementations8 Sep 2021 Maziar Gomrokchi, Susan Amin, Hossein Aboutalebi, Alexander Wong, Doina Precup

To address this gap, we propose an adversarial attack framework designed for testing the vulnerability of a state-of-the-art deep reinforcement learning algorithm to a membership inference attack.

Adversarial Attack Continuous Control +5

COVID-Net US: A Tailored, Highly Efficient, Self-Attention Deep Convolutional Neural Network Design for Detection of COVID-19 Patient Cases from Point-of-care Ultrasound Imaging

1 code implementation5 Aug 2021 Alexander MacLean, Saad Abbasi, Ashkan Ebadi, Andy Zhao, Maya Pavlova, Hayden Gunraj, Pengcheng Xi, Sonny Kohli, Alexander Wong

The Coronavirus Disease 2019 (COVID-19) pandemic has impacted many aspects of life globally, and a critical factor in mitigating its effects is screening individuals for infections, thereby allowing for both proper treatment for those individuals as well as action to be taken to prevent further spread of the virus.

LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution

1 code implementation ACL 2022 George Michalopoulos, Ian McKillop, Alexander Wong, Helen Chen

Contextual word embedding models have achieved state-of-the-art results in the lexical substitution task by relying on contextual information extracted from the replaced word within the sentence.

Sentence Sentence Similarity

Does Form Follow Function? An Empirical Exploration of the Impact of Deep Neural Network Architecture Design on Hardware-Specific Acceleration

no code implementations8 Jul 2021 Saad Abbasi, Mohammad Javad Shafiee, Ellick Chan, Alexander Wong

In this study, a comprehensive empirical exploration is conducted to investigate the impact of deep neural network architecture design on the degree of inference speedup that can be achieved via hardware-specific acceleration.

Neural Architecture Search

SALT: Sea lice Adaptive Lattice Tracking -- An Unsupervised Approach to Generate an Improved Ocean Model

no code implementations24 Jun 2021 Ju An Park, Vikram Voleti, Kathryn E. Thomas, Alexander Wong, Jason L. Deglint

Warming oceans due to climate change are leading to increased numbers of ectoparasitic copepods, also known as sea lice, which can cause significant ecological loss to wild salmon populations and major economic loss to aquaculture sites.

Management

Residual Error: a New Performance Measure for Adversarial Robustness

no code implementations18 Jun 2021 Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong

Motivated by this, this study presents the concept of residual error, a new performance measure for not only assessing the adversarial robustness of a deep neural network at the individual sample level, but also can be used to differentiate between adversarial and non-adversarial examples to facilitate for adversarial example detection.

Adversarial Robustness Image Classification

Insights into Data through Model Behaviour: An Explainability-driven Strategy for Data Auditing for Responsible Computer Vision Applications

no code implementations16 Jun 2021 Alexander Wong, Adam Dorfman, Paul McInnis, Hayden Gunraj

In this study, we take a departure and explore an explainability-driven strategy to data auditing, where actionable insights into the data at hand are discovered through the eyes of quantitative explainability on the behaviour of a dummy model prototype when exposed to data.

DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera

1 code implementation20 May 2021 William McNally, Pascale Walters, Kanav Vats, Alexander Wong, John McPhee

In the primary dataset containing 15k images captured from a face-on view of the dartboard using a smartphone, DeepDarts predicted the total score correctly in 94. 7% of the test images.

16k Data Augmentation +2

COVID-Net CXR-2: An Enhanced Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-ray Images

no code implementations14 May 2021 Maya Pavlova, Naomi Terhljan, Audrey G. Chung, Andy Zhao, Siddharth Surana, Hossein Aboutalebi, Hayden Gunraj, Ali Sabri, Amer Alaref, Alexander Wong

As the COVID-19 pandemic continues to devastate globally, the use of chest X-ray (CXR) imaging as a complimentary screening strategy to RT-PCR testing continues to grow given its routine clinical use for respiratory complaint.

Decision Making

COVID-Net CT-S: 3D Convolutional Neural Network Architectures for COVID-19 Severity Assessment using Chest CT Images

no code implementations4 May 2021 Hossein Aboutalebi, Saad Abbasi, Mohammad Javad Shafiee, Alexander Wong

The health and socioeconomic difficulties caused by the COVID-19 pandemic continues to cause enormous tensions around the world.

Management

COVID-Net CXR-S: Deep Convolutional Neural Network for Severity Assessment of COVID-19 Cases from Chest X-ray Images

no code implementations1 May 2021 Hossein Aboutalebi, Maya Pavlova, Mohammad Javad Shafiee, Ali Sabri, Amer Alaref, Alexander Wong

More specifically, we leveraged transfer learning to transfer representational knowledge gained from over 16, 000 CXR images from a multinational cohort of over 15, 000 patient cases into a custom network architecture for severity assessment.

Transfer Learning

AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge

no code implementations29 Apr 2021 Xiaoyu Wen, Mahmoud Famouri, Andrew Hryniowski, Alexander Wong

In this study, we introduce \textbf{AttendSeg}, a low-precision, highly compact deep neural network tailored for on-device semantic segmentation.

Segmentation Semantic Segmentation

Localization of Ice-Rink for Broadcast Hockey Videos

no code implementations22 Apr 2021 Mehrnaz Fani, Pascale Berunelle Walters, David A. Clausi, John Zelek, Alexander Wong

To localize the frames on the ice-rink model, a ResNet18-based regressor is implemented and trained, which regresses to four control points on the model in a frame-by-frame fashion.

Homography Estimation

TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases from Chest X-ray Images

1 code implementation6 Apr 2021 Alexander Wong, James Ren Hou Lee, Hadi Rahmat-Khah, Ali Sabri, Amer Alaref

Motivated by this pressing need and the recent recommendation by the World Health Organization (WHO) for the use of computer-aided diagnosis of TB, we introduce TB-Net, a self-attention deep convolutional neural network tailored for TB case screening.

Decision Making Specificity

COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analytics

2 code implementations18 Mar 2021 Ashkan Ebadi, Pengcheng Xi, Alexander MacLean, Stéphane Tremblay, Sonny Kohli, Alexander Wong

The COVID-19 pandemic continues to have a devastating effect on the health and well-being of the global population.

Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression from Chest CT Images

1 code implementation6 Mar 2021 Alexander Wong, Jack Lu, Adam Dorfman, Paul McInnis, Mahmoud Famouri, Daniel Manary, James Ren Hou Lee, Michael Lynch

Pulmonary fibrosis is a devastating chronic lung disease that causes irreparable lung tissue scarring and damage, resulting in progressive loss in lung capacity and has no known cure.

Computed Tomography (CT) Decision Making +1

COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning

1 code implementation19 Jan 2021 Hayden Gunraj, Ali Sabri, David Koff, Alexander Wong

We leverage explainability to investigate the decision-making behaviour of COVID-Net CT-2, with the results for select cases reviewed and reported on by two board-certified radiologists with over 10 and 30 years of experience, respectively.

Decision Making Specificity

A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning

no code implementations25 Dec 2020 Ahmadreza Jeddi, Mohammad Javad Shafiee, Alexander Wong

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks.

Adversarial Robustness Scheduling

Inter-layer Information Similarity Assessment of Deep Neural Networks Via Topological Similarity and Persistence Analysis of Data Neighbour Dynamics

no code implementations7 Dec 2020 Andrew Hryniowski, Alexander Wong

The quantitative analysis of information structure through a deep neural network (DNN) can unveil new insights into the theoretical performance of DNN architectures.

FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints

no code implementations30 Nov 2020 Stone Yun, Alexander Wong

Depth factorization and quantization have emerged as two of the principal strategies for designing efficient deep convolutional neural network (CNN) architectures tailored for low-power inference on the edge.

Quantization

Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks

no code implementations30 Nov 2020 Stone Yun, Alexander Wong

The fine-grained, layerwise analysis enables us to gain deep insights on how initial weights distributions will affect final accuracy and quantized behaviour.

Quantization

CancerNet-SCa: Tailored Deep Neural Network Designs for Detection of Skin Cancer from Dermoscopy Images

1 code implementation21 Nov 2020 James Ren Hou Lee, Maya Pavlova, Mahmoud Famouri, Alexander Wong

Motivated by the advances of deep learning and inspired by the open source initiatives in the research community, in this study we introduce CancerNet-SCa, a suite of deep neural network designs tailored for the detection of skin cancer from dermoscopy images that is open source and available to the general public as part of the Cancer-Net initiative.

Management

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer

1 code implementation17 Nov 2020 William McNally, Kanav Vats, Alexander Wong, John McPhee

Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks.

 Ranked #1 on Multi-Person Pose Estimation on MS COCO (Validation AP metric)

2D Human Pose Estimation Keypoint Detection +2

Identifying and interpreting tuning dimensions in deep networks

no code implementations NeurIPS Workshop SVRHM 2020 Nolan S. Dey, J. Eric Taylor, Bryan P. Tripp, Alexander Wong, Graham W. Taylor

While researchers have attempted to manually identify an analogue to these tuning dimensions in deep neural networks, we are unaware of an automatic way to discover them.

Attribute

Insights into Fairness through Trust: Multi-scale Trust Quantification for Financial Deep Learning

no code implementations3 Nov 2020 Alexander Wong, Andrew Hryniowski, Xiao Yu Wang

In this study we explore the feasibility and utility of a multi-scale trust quantification strategy to gain insights into the fairness of a financial deep learning model, particularly under different scenarios at different scales.

Fairness

UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus

1 code implementation NAACL 2021 George Michalopoulos, Yuanxin Wang, Hussam Kaka, Helen Chen, Alexander Wong

Contextual word embedding models, such as BioBERT and Bio_ClinicalBERT, have achieved state-of-the-art results in biomedical natural language processing tasks by focusing their pre-training process on domain-specific corpora.

named-entity-recognition Named Entity Recognition +3

Where's the Question? A Multi-channel Deep Convolutional Neural Network for Question Identification in Textual Data

1 code implementation15 Oct 2020 George Michalopoulos, Helen Chen, Alexander Wong

The gold standard in clinical data capturing is achieved via "expert-review", where clinicians can have a dialogue with a domain expert (reviewers) and ask them questions about data entry rules.

Sentence

Task-Driven Learning of Contour Integration Responses in a V1 Model

no code implementations NeurIPS Workshop SVRHM 2020 Salman Khan, Alexander Wong, Bryan P. Tripp

Under difficult viewing conditions, the brain's visual system uses a variety of modulatory techniques to augment its core feed-forward signals.

AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers

no code implementations30 Sep 2020 Alexander Wong, Mahmoud Famouri, Mohammad Javad Shafiee

Based on these promising results, AttendNets illustrate the effectiveness of visual attention condensers as building blocks for enabling various on-device visual perception tasks for TinyML applications.

Where Does Trust Break Down? A Quantitative Trust Analysis of Deep Neural Networks via Trust Matrix and Conditional Trust Densities

no code implementations30 Sep 2020 Andrew Hryniowski, Xiao Yu Wang, Alexander Wong

We experimentally leverage trust matrices to study several well-known deep neural network architectures for image recognition, and further study the trust density and conditional trust densities for an interesting actor-oracle answer scenario.

Product Recommendation

How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks

no code implementations12 Sep 2020 Alexander Wong, Xiao Yu Wang, Andrew Hryniowski

In this study, we take a step towards simple, interpretable metrics for trust quantification by introducing a suite of metrics for assessing the overall trustworthiness of deep neural networks based on their behaviour when answering a set of questions.

COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images

2 code implementations8 Sep 2020 Hayden Gunraj, Linda Wang, Alexander Wong

The coronavirus disease 2019 (COVID-19) pandemic continues to have a tremendous impact on patients and healthcare systems around the world.

Decision Making

TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices

no code implementations10 Aug 2020 Alexander Wong, Mahmoud Famouri, Maya Pavlova, Siddharth Surana

In this study, we introduce the concept of attention condensers for building low-footprint, highly-efficient deep neural networks for on-device speech recognition on the edge.

speech-recognition Speech Recognition

Vulnerability Under Adversarial Machine Learning: Bias or Variance?

no code implementations1 Aug 2020 Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong

In this study, we investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network and analyze how adversarial perturbations can affect the generalization of a network.

BIG-bench Machine Learning

Understanding the temporal evolution of COVID-19 research through machine learning and natural language processing

no code implementations22 Jul 2020 Ashkan Ebadi, Pengcheng Xi, Stéphane Tremblay, Bruce Spencer, Raman Pall, Alexander Wong

The outbreak of the novel coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been continuously affecting human lives and communities around the world in many ways, from cities under lockdown to new social experiences.

BIG-bench Machine Learning

Quantization in Relative Gradient Angle Domain For Building Polygon Estimation

no code implementations10 Jul 2020 Yuhao Chen, Yifan Wu, Linlin Xu, Alexander Wong

In this paper, we leverage the performance of CNNs, and propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs.

Quantization

EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-time Facial Expression Recognition

1 code implementation29 Jun 2020 James Ren Hou Lee, Linda Wang, Alexander Wong

While recent advances in deep learning have led to significant improvements in facial expression classification (FEC), a major challenge that remains a bottleneck for the widespread deployment of such systems is their high architectural and computational complexities.

Facial Expression Recognition Facial Expression Recognition (FER) +1

COVID-Net S: Towards computer-aided severity assessment via training and validation of deep neural networks for geographic extent and opacity extent scoring of chest X-rays for SARS-CoV-2 lung disease severity

2 code implementations26 May 2020 Alexander Wong, Zhong Qiu Lin, Linda Wang, Audrey G. Chung, Beiyi Shen, Almas Abbasi, Mahsa Hoshmand-Kochi, Timothy Q. Duong

Findings: The COVID-Net S deep neural networks yielded R$^2$ of 0. 664 $\pm$ 0. 032 and 0. 635 $\pm$ 0. 044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments.

DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation

no code implementations17 Apr 2020 Linda Wang, Mahmoud Famouri, Alexander Wong

The result is a compact deep neural network with highly customized macroarchitecture and microarchitecture designs, as well as self-normalizing characteristics, that are highly tailored for the task of embedded depth estimation.

Autonomous Vehicles Monocular Depth Estimation

COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images

16 code implementations22 Mar 2020 Linda Wang, Alexander Wong

Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public.

COVID-19 Diagnosis

Deep Neural Network Perception Models and Robust Autonomous Driving Systems

no code implementations4 Mar 2020 Mohammad Javad Shafiee, Ahmadreza Jeddi, Amir Nazemi, Paul Fieguth, Alexander Wong

This paper analyzes the robustness of deep learning models in autonomous driving applications and discusses the practical solutions to address that.

Autonomous Driving

TimeConvNets: A Deep Time Windowed Convolution Neural Network Design for Real-time Video Facial Expression Recognition

no code implementations3 Mar 2020 James Ren Hou Lee, Alexander Wong

A core challenge faced by the majority of individuals with Autism Spectrum Disorder (ASD) is an impaired ability to infer other people's emotions based on their facial expressions.

Facial Expression Recognition Facial Expression Recognition (FER)

Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis

no code implementations14 Jan 2020 Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong

As such, there has been a recent focus on unsupervised learning approaches to mitigate the data annotation issue; however, current approaches in literature have limited performance compared to supervised learning approaches as well as limited applicability for adoption in new environments.

Clustering Person Re-Identification +2

Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification

no code implementations9 Jan 2020 Chris Dulhanty, Alexander Wong

This modest difference in accuracy demonstrates that face recognition systems using deep learning work better for individuals they are trained on, which has serious privacy implications when one considers all major open source face recognition training datasets do not obtain informed consent from individuals during their collection.

Face Identification Face Recognition +1

Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection

no code implementations27 Nov 2019 Chris Dulhanty, Jason L. Deglint, Ibrahim Ben Daya, Alexander Wong

The exponential rise of social media and digital news in the past decade has had the unfortunate consequence of escalating what the United Nations has called a global topic of concern: the growing prevalence of disinformation.

Language Modelling Stance Detection +2

DeepLABNet: End-to-end Learning of Deep Radial Basis Networks with Fully Learnable Basis Functions

no code implementations21 Nov 2019 Andrew Hryniowski, Alexander Wong

In this work, we present a novel approach that enables end-to-end learning of deep RBF networks with fully learnable activation basis functions in an automatic and tractable manner.

When Segmentation is Not Enough: Rectifying Visual-Volume Discordance Through Multisensor Depth-Refined Semantic Segmentation for Food Intake Tracking in Long-Term Care

no code implementations24 Oct 2019 Kaylen J. Pfisterer, Robert Amelard, Audrey G. Chung, Braeden Syrnyk, Alexander MacLean, Heather H Keller, Alexander Wong

We propose a novel deep convolutional encoder-decoder food network with depth-refinement (EDFN-D) using an RGB-D camera for quantifying a plate's remaining food volume relative to reference portions in whole and modified texture foods.

Decoder General Classification +2

Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms

no code implementations16 Oct 2019 Zhong Qiu Lin, Mohammad Javad Shafiee, Stanislav Bochkarev, Michael St. Jules, Xiao Yu Wang, Alexander Wong

A comprehensive analysis using this approach was conducted on several state-of-the-art explainability methods (LIME, SHAP, Expected Gradients, GSInquire) on a ResNet-50 deep convolutional neural network using a subset of ImageNet for the task of image classification.

Decision Making Explainable artificial intelligence +2

State of Compact Architecture Search For Deep Neural Networks

no code implementations15 Oct 2019 Mohammad Javad Shafiee, Andrew Hryniowski, Francis Li, Zhong Qiu Lin, Alexander Wong

A particularly interesting class of compact architecture search algorithms are those that are guided by baseline network architectures.

YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection

4 code implementations3 Oct 2019 Alexander Wong, Mahmoud Famuori, Mohammad Javad Shafiee, Francis Li, Brendan Chwyl, Jonathan Chung

As such, there has been growing research interest in the design of efficient deep neural network architectures catered for edge and mobile usage.

Object object-detection +1

Squeeze-and-Attention Networks for Semantic Segmentation

1 code implementation CVPR 2020 Zilong Zhong, Zhong Qiu Lin, Rene Bidart, Xiaodan Hu, Ibrahim Ben Daya, Zhifeng Li, Wei-Shi Zheng, Jonathan Li, Alexander Wong

The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features.

Segmentation Semantic Segmentation

Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID

no code implementations28 Jul 2019 Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong

There has been recent interest in tackling this challenge using cross-domain approaches, which leverages data from source domains that are different than the target domain.

Person Re-Identification

Food for thought: Ethical considerations of user trust in computer vision

no code implementations29 May 2019 Kaylen J. Pfisterer, Jennifer Boger, Alexander Wong

In computer vision research, especially when novel applications of tools are developed, ethical implications around user perceptions of trust in the underlying technology should be considered and supported.

Decision Making

Seeing Convolution Through the Eyes of Finite Transformation Semigroup Theory: An Abstract Algebraic Interpretation of Convolutional Neural Networks

no code implementations26 May 2019 Andrew Hryniowski, Alexander Wong

Researchers are actively trying to gain better insights into the representational properties of convolutional neural networks for guiding better network designs and for interpreting a network's computational nature.

Network Interpretation

Enabling Computer Vision Driven Assistive Devices for the Visually Impaired via Micro-architecture Design Exploration

no code implementations20 May 2019 Linda Wang, Alexander Wong

To address these challenges, this study investigates creating an efficient object detection network specifically for OLIV, an AI-powered assistant for object localization for the visually impaired, via micro-architecture design exploration.

Object object-detection +2

Affine Variational Autoencoders: An Efficient Approach for Improving Generalization and Robustness to Distribution Shift

no code implementations13 May 2019 Rene Bidart, Alexander Wong

In this study, we propose the Affine Variational Autoencoder (AVAE), a variant of Variational Autoencoder (VAE) designed to improve robustness by overcoming the inability of VAEs to generalize to distributional shifts in the form of affine perturbations.

Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification

no code implementations12 May 2019 Zilong Zhong, Jonathan Li, David A. Clausi, Alexander Wong

In this paper, we address the hyperspectral image (HSI) classification task with a generative adversarial network and conditional random field (GAN-CRF) -based framework, which integrates a semi-supervised deep learning and a probabilistic graphical model, and make three contributions.

Classification General Classification +2

EdgeSegNet: A Compact Network for Semantic Segmentation

1 code implementation10 May 2019 Zhong Qiu Lin, Brendan Chwyl, Alexander Wong

In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation.

Segmentation Semantic Segmentation

Auditing ImageNet: Towards a Model-driven Framework for Annotating Demographic Attributes of Large-Scale Image Datasets

no code implementations3 May 2019 Chris Dulhanty, Alexander Wong

The ImageNet dataset ushered in a flood of academic and industry interest in deep learning for computer vision applications.

Object Recognition

Towards computer vision powered color-nutrient assessment of pureed food

no code implementations1 May 2019 Kaylen J. Pfisterer, Robert Amelard, Braeden Syrnyk, Alexander Wong

With one in four individuals afflicted with malnutrition, computer vision may provide a way of introducing a new level of automation in the nutrition field to reliably monitor food and nutrient intake.

Nutrition

Beyond Explainability: Leveraging Interpretability for Improved Adversarial Learning

no code implementations21 Apr 2019 Devinder Kumar, Ibrahim Ben-Daya, Kanav Vats, Jeffery Feng, Graham Taylor and, Alexander Wong

In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability.

Assessing Architectural Similarity in Populations of Deep Neural Networks

no code implementations19 Apr 2019 Audrey Chung, Paul Fieguth, Alexander Wong

Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the synthesis of increasingly efficient architectures over successive generations.

KPTransfer: improved performance and faster convergence from keypoint subset-wise domain transfer in human pose estimation

no code implementations24 Mar 2019 Kanav Vats, Helmut Neher, Alexander Wong, David A. Clausi, John Zelek

This approach is motivated by the notion that rich contextual knowledge can be transferred between different keypoint subsets representing separate domains.

Keypoint Detection

AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design

no code implementations18 Mar 2019 Alexander Wong, Zhong Qiu Lin, Brendan Chwyl

Furthermore, the efficacy of the AttoNets is demonstrated for the task of instance-level object segmentation and object detection, where an AttoNet-based Mask R-CNN network was constructed with significantly fewer parameters and computational costs (~5x fewer multiply-add operations and ~2x fewer parameters) than a ResNet-50 based Mask R-CNN network.

object-detection Object Detection +2

GolfDB: A Video Database for Golf Swing Sequencing

1 code implementation15 Mar 2019 William McNally, Kanav Vats, Tyler Pinto, Chris Dulhanty, John McPhee, Alexander Wong

The golf swing is a complex movement requiring considerable full-body coordination to execute proficiently.

STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection

no code implementations26 Feb 2019 William McNally, Alexander Wong, John McPhee

As such, there has been recent interest on human action recognition using low-cost, readily-available RGB cameras via deep convolutional neural networks.

Action Recognition Multimodal Activity Recognition +3

Democratisation of Usable Machine Learning in Computer Vision

no code implementations18 Feb 2019 Raymond Bond, Ansgar Koene, Alan Dix, Jennifer Boger, Maurice D. Mulvenna, Mykola Galushka, Bethany Waterhouse Bradley, Fiona Browne, Hui Wang, Alexander Wong

Many industries are now investing heavily in data science and automation to replace manual tasks and/or to help with decision making, especially in the realm of leveraging computer vision to automate many monitoring, inspection, and surveillance tasks.

BIG-bench Machine Learning Decision Making

Progressive Label Distillation: Learning Input-Efficient Deep Neural Networks

no code implementations26 Jan 2019 Zhong Qiu Lin, Alexander Wong

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network.

Knowledge Distillation speech-recognition +1

SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells

no code implementations15 Jan 2019 Vignesh Sankar, Devinder Kumar, David A. Clausi, Graham W. Taylor, Alexander Wong

Conclusion: The SISC radiomic sequencer is able to achieve state-of-the-art results in lung cancer prediction, and also offers prediction interpretability in the form of critical response maps.

Computed Tomography (CT) Decision Making

Mitigating Architectural Mismatch During the Evolutionary Synthesis of Deep Neural Networks

no code implementations19 Nov 2018 Audrey Chung, Paul Fieguth, Alexander Wong

Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the organic synthesis of increasingly efficient architectures over successive generations.

ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks

no code implementations14 Nov 2018 Xiaodan Hu, Audrey G. Chung, Paul Fieguth, Farzad Khalvati, Masoom A. Haider, Alexander Wong

Generative Adversarial Networks (GANs) have shown considerable promise for mitigating the challenge of data scarcity when building machine learning-driven analysis algorithms.

Data Augmentation Image Generation

PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations

no code implementations10 Nov 2018 Andrew Hryniowski, Alexander Wong

However, this attention has not been equally shared by one of the fundamental building blocks of a deep neural network, the neurons.

SRP: Efficient class-aware embedding learning for large-scale data via supervised random projections

1 code implementation7 Nov 2018 Amir-Hossein Karimi, Alexander Wong, Ali Ghodsi

While stochastic approximation strategies have been explored for unsupervised dimensionality reduction to tackle this challenge, such approaches are not well-suited for accelerating computational speed for supervised dimensionality reduction.

Supervised dimensionality reduction

Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates

no code implementations5 Nov 2018 Mohammad Saeed Shafiee, Mohammad Javad Shafiee, Alexander Wong

The proposed d-gate modules can be integrated with any deep neural network and reduces the average computational cost of the deep neural networks while maintaining modeling accuracy.

Investigating the Automatic Classification of Algae Using Fusion of Spectral and Morphological Characteristics of Algae via Deep Residual Learning

no code implementations25 Oct 2018 Jason L. Deglint, Chao Jin, Alexander Wong

This high level of accuracy was achieved using a deep residual convolutional neural network that learns the optimal combination of spectral and morphological features.

BIG-bench Machine Learning General Classification +1

EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge

no code implementations18 Oct 2018 Zhong Qiu Lin, Audrey G. Chung, Alexander Wong

Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices.

speech-recognition Speech Recognition

Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates

no code implementations NIPS Workshop CDNNRIA 2018 Mohammad Saeed Shafiee, Mohammad Javad Shafiee, Alexander Wong

The current trade-off between depth and computational cost makes it difficult to adopt deep neural networks for many industrial applications, especially when computing power is limited.

FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis

no code implementations17 Sep 2018 Alexander Wong, Mohammad Javad Shafiee, Brendan Chwyl, Francis Li

In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements.

Image Classification object-detection +2

TriResNet: A Deep Triple-stream Residual Network for Histopathology Grading

no code implementations22 Jun 2018 Rene Bidart, Alexander Wong

While microscopic analysis of histopathological slides is generally considered as the gold standard method for performing cancer diagnosis and grading, the current method for analysis is extremely time consuming and labour intensive as it requires pathologists to visually inspect tissue samples in a detailed fashion for the presence of cancer.

NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage

no code implementations14 Jun 2018 Alexander Wong

Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such as mobile and other consumer devices given their high computational and memory requirements.

Image Classification Object Recognition

Unsupervised Feature Learning Toward a Real-time Vehicle Make and Model Recognition

no code implementations8 Jun 2018 Amir Nazemi, Mohammad Javad Shafiee, Zohreh Azimifar, Alexander Wong

Here, we formulate the vehicle make and model recognition as a fine-grained classification problem and propose a new configurable on-road vehicle make and model recognition framework.

The feasibility of automated identification of six algae types using neural networks and fluorescence-based spectral-morphological features

no code implementations3 May 2018 Jason L. Deglint, Chao Jin, Angela Chao, Alexander Wong

A number of morphological and spectral fluorescence features are then extracted from the isolated micro-organism imaging data, and used to train neural network classification models designed for the purpose of identification of the six algae types given an isolated micro-organism.

BIG-bench Machine Learning General Classification

MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-time Embedded Traffic Sign Classification

1 code implementation28 Mar 2018 Alexander Wong, Mohammad Javad Shafiee, Michael St. Jules

The resulting MicronNet possesses a model size of just ~1MB and ~510, 000 parameters (~27x fewer parameters than state-of-the-art) while still achieving a human performance level top-1 accuracy of 98. 9% on the German traffic sign recognition benchmark.

General Classification Traffic Sign Recognition

Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection

1 code implementation19 Feb 2018 Alexander Wong, Mohammad Javad Shafiee, Francis Li, Brendan Chwyl

The resulting Tiny SSD possess a model size of 2. 3MB (~26X smaller than Tiny YOLO) while still achieving an mAP of 61. 3% on VOC 2007 (~4. 2% higher than Tiny YOLO).

Object object-detection +2

Nature vs. Nurture: The Role of Environmental Resources in Evolutionary Deep Intelligence

no code implementations9 Feb 2018 Audrey G. Chung, Paul Fieguth, Alexander Wong

Evolutionary deep intelligence synthesizes highly efficient deep neural networks architectures over successive generations.

StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks

no code implementations16 Jan 2018 Mohammad Javad Shafiee, Brendan Chwyl, Francis Li, Rongyan Chen, Michelle Karg, Christian Scharfenberger, Alexander Wong

The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption, particularly for use in embedded devices.

object-detection Object Detection

JADE: Joint Autoencoders for Dis-Entanglement

no code implementations24 Nov 2017 Ershad Banijamali, Amir-Hossein Karimi, Alexander Wong, Ali Ghodsi

The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis.

Disentanglement General Classification

SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis

no code implementations20 Nov 2017 Mohammad Javad Shafiee, Francis Li, Brendan Chwyl, Alexander Wong

While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread deployment on edge devices such as mobile and other consumer devices is high computational and memory requirements.

Discovery Radiomics with CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy

no code implementations29 Oct 2017 Devinder Kumar, Graham W. Taylor, Alexander Wong

Conclusion: We demonstrate the effectiveness and utility of the proposed CLEAR-DR system of enhancing the interpretability of diagnostic grading results for the application of diabetic retinopathy grading.

Decision Making Diabetic Retinopathy Grading

Discovery Radiomics via Deep Multi-Column Radiomic Sequencers for Skin Cancer Detection

no code implementations24 Sep 2017 Mohammad Javad Shafiee, Alexander Wong

While skin cancer is the most diagnosed form of cancer in men and women, with more cases diagnosed each year than all other cancers combined, sufficiently early diagnosis results in very good prognosis and as such makes early detection crucial.

Specificity

Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video

1 code implementation18 Sep 2017 Mohammad Javad Shafiee, Brendan Chywl, Francis Li, Alexander Wong

Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene.

Object object-detection +2

The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis

no code implementations7 Sep 2017 Audrey Chung, Mohammad Javad Shafiee, Paul Fieguth, Alexander Wong

Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations.