Search Results for author: Graham W. Taylor

Found 83 papers, 34 papers with code

Which Tokens to Use? Investigating Token Reduction in Vision Transformers

1 code implementation9 Aug 2023 Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, Thomas B. Moeslund

While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets.

Classification Image Classification

Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data

no code implementations3 Jul 2023 Kevin Kasa, Graham W. Taylor

Here, we characterize the performance of several post-hoc and training-based conformal prediction methods under these settings, providing the first empirical evaluation on large-scale datasets and models.

Conformal Prediction

Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers

no code implementations CVPR 2023 Cong Wei, Brendan Duke, Ruowei Jiang, Parham Aarabi, Graham W. Taylor, Florian Shkurti

Equipped with the learned unstructured attention pattern, sparse attention ViT (Sparsifiner) produces a superior Pareto-optimal trade-off between FLOPs and top-1 accuracy on ImageNet compared to token sparsity.

GCNet: Probing Self-Similarity Learning for Generalized Counting Network

no code implementations10 Feb 2023 Mingjie Wang, Yande Li, Jun Zhou, Graham W. Taylor, Minglun Gong

The class-agnostic counting (CAC) problem has caught increasing attention recently due to its wide societal applications and arduous challenges.

Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition

2 code implementations19 Jan 2023 Juan Carrasquilla, Mohamed Hibat-Allah, Estelle Inack, Alireza Makhzani, Kirill Neklyudov, Graham W. Taylor, Giacomo Torlai

Binary neural networks, i. e., neural networks whose parameters and activations are constrained to only two possible values, offer a compelling avenue for the deployment of deep learning models on energy- and memory-limited devices.

Combinatorial Optimization

Bounding generalization error with input compression: An empirical study with infinite-width networks

no code implementations19 Jul 2022 Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, Graham W. Taylor

Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data.

Monitoring Shortcut Learning using Mutual Information

no code implementations27 Jun 2022 Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor

The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critical domains such as healthcare, finance and autonomous vehicles.

Autonomous Vehicles

Understanding the impact of image and input resolution on deep digital pathology patch classifiers

no code implementations29 Apr 2022 Eu Wern Teh, Graham W. Taylor

Our experiments show that patch classification performance can be improved by manipulating both the image and input resolution in annotation-scarce and annotation-rich environments.


DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software

no code implementations29 Jan 2022 Chuan-Yung Tsai, Graham W. Taylor

Although machine learning (ML) has been successful in automating various software engineering needs, software testing still remains a highly challenging topic.

reinforcement-learning Reinforcement Learning (RL)

On Evaluation Metrics for Graph Generative Models

1 code implementation ICLR 2022 Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor

While we focus on applying these metrics to GGM evaluation, in practice this enables the ability to easily compute the dissimilarity between any two sets of graphs regardless of domain.

Image Generation Model Selection

Learning with Less Labels in Digital Pathology via Scribble Supervision from Natural Images

no code implementations7 Jan 2022 Eu Wern Teh, Graham W. Taylor

Furthermore, we show that models trained with scribble labels yield the same performance boost as full pixel-wise segmentation labels despite being significantly easier and faster to collect.

Transfer Learning

Domain-Agnostic Clustering with Self-Distillation

no code implementations23 Nov 2021 Mohammed Adnan, Yani A. Ioannou, Chuan-Yung Tsai, Graham W. Taylor

Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning.

Clustering Data Augmentation +4

Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning

no code implementations NeurIPS 2021 Hyunsoo Chung, Jungtaek Kim, Boris Knyazev, Jinhwi Lee, Graham W. Taylor, Jaesik Park, Minsu Cho

Discovering a solution in a combinatorial space is prevalent in many real-world problems but it is also challenging due to diverse complex constraints and the vast number of possible combinations.

reinforcement-learning Reinforcement Learning (RL)

Parameter Prediction for Unseen Deep Architectures

1 code implementation NeurIPS 2021 Boris Knyazev, Michal Drozdzal, Graham W. Taylor, Adriana Romero-Soriano

We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet.

Parameter Prediction

Neural Structure Mapping For Learning Abstract Visual Analogies

no code implementations NeurIPS Workshop SVRHM 2021 Shashank Shekhar, Graham W. Taylor

Our framework uses (1) a multi-task visual relationship encoder to extract constituent concepts from raw visual input in the source domain, and (2) a neural module net analogy inference engine to reason compositionally about the inferred relation in the target domain.

Visual Analogies Visual Reasoning

Unconstrained Scene Generation with Locally Conditioned Radiance Fields

1 code implementation ICCV 2021 Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind

In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.

Scene Generation

LOHO: Latent Optimization of Hairstyles via Orthogonalization

1 code implementation CVPR 2021 Rohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi

Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer.


Building LEGO Using Deep Generative Models of Graphs

1 code implementation21 Dec 2020 Rylee Thompson, Elahe Ghalebi, Terrance DeVries, Graham W. Taylor

Generative models are now used to create a variety of high-quality digital artifacts.

Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization

no code implementations NeurIPS Workshop LMCA 2020 Michal Lisicki, Arash Afkanpour, Graham W. Taylor

Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems.

Combinatorial Optimization Efficient Neural Network +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.

Instance Selection for GANs

1 code implementation NeurIPS 2020 Terrance DeVries, Michal Drozdzal, Graham W. Taylor

By refining the empirical data distribution before training, we redirect model capacity towards high-density regions, which ultimately improves sample fidelity, lowers model capacity requirements, and significantly reduces training time.

Conditional Image Generation

Enabling Continual Learning with Differentiable Hebbian Plasticity

no code implementations30 Jun 2020 Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor

Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge.

Continual Learning Permuted-MNIST +1

Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation

1 code implementation17 May 2020 Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham W. Taylor, Aaron Courville, Eugene Belilovsky

We show that such models can suffer the most in their ability to generalize to rare compositions, evaluating two different models on the Visual Genome dataset and its more recent, improved version, GQA.

Graph Generation Scene Graph Generation

Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task

no code implementations28 Apr 2020 Katya Kudashkina, Valliappa Chockalingam, Graham W. Taylor, Michael Bowling

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis.

Model-based Reinforcement Learning

ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

1 code implementation ECCV 2020 Eu Wern Teh, Terrance DeVries, Graham W. Taylor

Additionally, our proposed fast moving proxies also addresses small gradient issue of proxies, and this component synergizes well with low temperature scaling and Global Max Pooling.

Image Retrieval Metric Learning +1

Learning with less data via Weakly Labeled Patch Classification in Digital Pathology

2 code implementations27 Nov 2019 Eu Wern Teh, Graham W. Taylor

In Digital Pathology (DP), labeled data is generally very scarce due to the requirement that medical experts provide annotations.

General Classification

A Nonparametric Bayesian Model for Sparse Dynamic Multigraphs

no code implementations11 Oct 2019 Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham W. Taylor, Sinead A. Williamson

As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure that underpins these interactions.


Differentiable Hebbian Consolidation for Continual Learning

no code implementations25 Sep 2019 Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor

Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge.

Continual Learning Permuted-MNIST +1

Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions

1 code implementation23 Sep 2019 Boris Knyazev, Carolyn Augusta, Graham W. Taylor

We consider a common case in which edges can be short term interactions (e. g., messaging) or long term structural connections (e. g., friendship).

Dynamic Link Prediction Point Processes

Image Classification with Hierarchical Multigraph Networks

1 code implementation21 Jul 2019 Boris Knyazev, Xiao Lin, Mohamed R. Amer, Graham W. Taylor

Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data.

Classification General Classification +3

On the Evaluation of Conditional GANs

1 code implementation11 Jul 2019 Terrance DeVries, Adriana Romero, Luis Pineda, Graham W. Taylor, Michal Drozdzal

We show that FJD can be used as a promising single metric for cGAN benchmarking and model selection.

Benchmarking Model Selection

Sequential Edge Clustering in Temporal Multigraphs

no code implementations28 May 2019 Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham W. Taylor, Sinead A. Williamson

Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner.


Understanding Attention and Generalization in Graph Neural Networks

2 code implementations NeurIPS 2019 Boris Knyazev, Graham W. Taylor, Mohamed R. Amer

We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness.

Graph Classification

Batch Normalization is a Cause of Adversarial Vulnerability

no code implementations6 May 2019 Angus Galloway, Anna Golubeva, Thomas Tanay, Medhat Moussa, Graham W. Taylor

Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks.

Similarity Learning Networks for Animal Individual Re-Identification -- Beyond the Capabilities of a Human Observer

no code implementations21 Feb 2019 Stefan Schneider, Graham W. Taylor, Stefan Linquist, Stefan C. Kremer

Without any species-specific modifications, our results demonstrate that similarity comparison networks can reach a performance level beyond that of humans for the task of animal re-identification.

Object Detection One-Shot Learning

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

Adversarial Examples as an Input-Fault Tolerance Problem

1 code implementation30 Nov 2018 Angus Galloway, Anna Golubeva, Graham W. Taylor

We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input.

Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

1 code implementation23 Nov 2018 Boris Knyazev, Xiao Lin, Mohamed R. Amer, Graham W. Taylor

Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data.

General Classification Graph Classification +1

Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data

no code implementations19 Nov 2018 Stefan Schneider, Graham W. Taylor, Stefan S. Linquist, Stefan C. Kremer

The ability of a researcher to re-identify (re-ID) an individual animal upon re-encounter is fundamental for addressing a broad range of questions in the study of ecosystem function, community and population dynamics, and behavioural ecology.

Feature Engineering object-detection +1

A Rate-Distortion Theory of Adversarial Examples

no code implementations27 Sep 2018 Angus Galloway, Anna Golubeva, Graham W. Taylor

The generalization ability of deep neural networks (DNNs) is intertwined with model complexity, robustness, and capacity.

Self-Paced Learning with Adaptive Deep Visual Embeddings

1 code implementation24 Jul 2018 Vithursan Thangarasa, Graham W. Taylor

Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge.

Fine-Grained Visual Recognition Image Classification +2

Stochastic Layer-Wise Precision in Deep Neural Networks

no code implementations3 Jul 2018 Griffin Lacey, Graham W. Taylor, Shawki Areibi

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks.

Leveraging Uncertainty Estimates for Predicting Segmentation Quality

no code implementations2 Jul 2018 Terrance DeVries, Graham W. Taylor

The first is producing spatial uncertainty maps, from which a clinician can observe where and why a system thinks it is failing.

Adversarial Training Versus Weight Decay

2 code implementations10 Apr 2018 Angus Galloway, Thomas Tanay, Graham W. Taylor

Performance-critical machine learning models should be robust to input perturbations not seen during training.

Deep Learning Object Detection Methods for Ecological Camera Trap Data

no code implementations28 Mar 2018 Stefan Schneider, Graham W. Taylor, Stefan C. Kremer

Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images.

object-detection Object Detection +2

Generalized Hadamard-Product Fusion Operators for Visual Question Answering

no code implementations26 Mar 2018 Brendan Duke, Graham W. Taylor

We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA).

Neural Architecture Search Question Answering +1

Real-Time End-to-End Action Detection with Two-Stream Networks

no code implementations23 Feb 2018 Alaaeldin El-Nouby, Graham W. Taylor

Finally, for better network initialization, we transfer from the task of action recognition to action detection by pre-training our framework using the recently released large-scale Kinetics dataset.

Action Detection Action Recognition +3

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

1 code implementation CVPR 2018 Fabien Baradel, Christian Wolf, Julien Mille, Graham W. Taylor

No spatial coherence is forced on the glimpse locations, which gives the module liberty to explore different points at each frame and better optimize the process of scrutinizing visual information.

Action Recognition Activity Prediction +3

Learning Confidence for Out-of-Distribution Detection in Neural Networks

4 code implementations13 Feb 2018 Terrance DeVries, Graham W. Taylor

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong.

Out-of-Distribution Detection

Predicting Adversarial Examples with High Confidence

no code implementations13 Feb 2018 Angus Galloway, Graham W. Taylor, Medhat Moussa

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence.

Data Augmentation Vocal Bursts Intensity Prediction

LEAP: Learning Embeddings for Adaptive Pace

no code implementations ICLR 2018 Vithursan Thangarasa, Graham W. Taylor

The \textit{student} CNN classifier dynamically selects samples to form a mini-batch based on the \textit{easiness} from cross-entropy losses and \textit{true diverseness} of examples from the representation space sculpted by the \textit{embedding} CNN.

Image Classification Metric Learning +1

Bit-Regularized Optimization of Neural Nets

no code implementations ICLR 2018 Mohamed Amer, Aswin Raghavan, Graham W. Taylor, Sek Chai

Our key idea is to control the expressive power of the network by dynamically quantizing the range and set of values that the parameters can take.


Attacking Binarized Neural Networks

1 code implementation ICLR 2018 Angus Galloway, Graham W. Taylor, Medhat Moussa

Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents.


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

Improved Regularization of Convolutional Neural Networks with Cutout

26 code implementations15 Aug 2017 Terrance DeVries, Graham W. Taylor

Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.

Domain Generalization Image Augmentation +2

Structure Optimization for Deep Multimodal Fusion Networks using Graph-Induced Kernels

no code implementations3 Jul 2017 Dhanesh Ramachandram, Michal Lisicki, Timothy J. Shields, Mohamed R. Amer, Graham W. Taylor

A popular testbed for deep learning has been multimodal recognition of human activity or gesture involving diverse inputs such as video, audio, skeletal pose and depth images.

Bayesian Optimization Human Activity Recognition

Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks

no code implementations13 Apr 2017 Devinder Kumar, Alexander Wong, Graham W. Taylor

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand the decisions made by deep neural networks (DNNs) given a specific input.

Decision Making

The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment

no code implementations18 Feb 2017 Angus Galloway, Graham W. Taylor, Aaron Ramsay, Medhat Moussa

An original dataset for semantic segmentation, Ciona17, is introduced, which to the best of the authors' knowledge, is the first dataset of its kind with pixel-level annotations pertaining to invasive species in a marine environment.

Semantic Segmentation

Dataset Augmentation in Feature Space

2 code implementations17 Feb 2017 Terrance DeVries, Graham W. Taylor

Our main insight is to perform the transformation not in input space, but in a learned feature space.

Representation Learning

Modeling Grasp Motor Imagery through Deep Conditional Generative Models

no code implementations11 Jan 2017 Matthew Veres, Medhat Moussa, Graham W. Taylor

Grasping is a complex process involving knowledge of the object, the surroundings, and of oneself.

Understanding Anatomy Classification Through Attentive Response Maps

no code implementations19 Nov 2016 Devinder Kumar, Vlado Menkovski, Graham W. Taylor, Alexander Wong

One of the main challenges for broad adoption of deep learning based models such as convolutional neural networks (CNN), is the lack of understanding of their decisions.

Anatomy Classification +1

Learning a metric for class-conditional KNN

1 code implementation11 Jul 2016 Daniel Jiwoong Im, Graham W. Taylor

To extend its applicability outside of image-based domains, we propose to learn a metric which captures perceptual similarity.

Classification General Classification +2

Theano-MPI: a Theano-based Distributed Training Framework

1 code implementation26 May 2016 He Ma, Fei Mao, Graham W. Taylor

We develop a scalable and extendable training framework that can utilize GPUs across nodes in a cluster and accelerate the training of deep learning models based on data parallelism.

Deep Learning on FPGAs: Past, Present, and Future

no code implementations13 Feb 2016 Griffin Lacey, Graham W. Taylor, Shawki Areibi

The rapid growth of data size and accessibility in recent years has instigated a shift of philosophy in algorithm design for artificial intelligence.

Philosophy speech-recognition +1

ModDrop: adaptive multi-modal gesture recognition

no code implementations31 Dec 2014 Natalia Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout

We present a method for gesture detection and localisation based on multi-scale and multi-modal deep learning.

Gesture Recognition

Scoring and Classifying with Gated Auto-encoders

no code implementations20 Dec 2014 Daniel Jiwoong Im, Graham W. Taylor

In this work, we apply a dynamical systems view to GAEs, deriving a scoring function, and drawing connections to Restricted Boltzmann Machines.

General Classification Multi-Label Classification +1

Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics

1 code implementation20 Dec 2014 Daniel Jiwoong Im, Ethan Buchman, Graham W. Taylor

Here we propose a more general form for the sampling dynamics in MPF, and explore the consequences of different choices for these dynamics for training RBMs.

"Mental Rotation" by Optimizing Transforming Distance

no code implementations11 Jun 2014 Weiguang Ding, Graham W. Taylor

The human visual system is able to recognize objects despite transformations that can drastically alter their appearance.

Data Augmentation

Learning Human Pose Estimation Features with Convolutional Networks

1 code implementation27 Dec 2013 Arjun Jain, Jonathan Tompson, Mykhaylo Andriluka, Graham W. Taylor, Christoph Bregler

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models.

Object Recognition Pose Estimation +2

Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines

no code implementations NeurIPS 2011 Matthew D. Zeiler, Graham W. Taylor, Leonid Sigal, Iain Matthews, Rob Fergus

We present a type of Temporal Restricted Boltzmann Machine that defines a probability distribution over an output sequence conditional on an input sequence.

Pose-Sensitive Embedding by Nonlinear NCA Regression

no code implementations NeurIPS 2010 Graham W. Taylor, Rob Fergus, George Williams, Ian Spiro, Christoph Bregler

We apply our method to challenging real-world data and show that it can generalize beyond hand localization to infer a more general notion of body pose.


The Recurrent Temporal Restricted Boltzmann Machine

no code implementations NeurIPS 2008 Ilya Sutskever, Geoffrey E. Hinton, Graham W. Taylor

The Temporal Restricted Boltzmann Machine (TRBM) is a probabilistic model for sequences that is able to successfully model (i. e., generate nice-looking samples of) several very high dimensional sequences, such as motion capture data and the pixels of low resolution videos of balls bouncing in a box.

Cannot find the paper you are looking for? You can Submit a new open access paper.