Search Results for author:
Found 77 papers, 36 papers with code
On Transferability of Histological Tissue Labels in Computational Pathology
Deep learning tools in computational pathology, unlike natural vision tasks, face with limited histological tissue labels for classification.
Wonderland: Navigating 3D Scenes from a Single Image
Specifically, we introduce a large-scale reconstruction model that uses latents from a video diffusion model to predict 3D Gaussian Splattings for the scenes in a feed-forward manner.
Data-to-Model Distillation: Data-Efficient Learning Framework
In this paper, we propose a novel framework called Data-to-Model Distillation (D2M) to distill the real dataset's knowledge into the learnable parameters of a pre-trained generative model by aligning rich representations extracted from real and generated images.
Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks
This framework distills the aggregated knowledge of IoT devices to a prompt generator to efficiently adapt the frozen FM for downstream tasks.
Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC).
Ranked #1 on
Video Polyp Segmentation
on SUN-SEG-Hard (Unseen)
GSTAM: Efficient Graph Distillation with Structural Attention-Matching
Graph distillation has emerged as a solution for reducing large graph datasets to smaller, more manageable, and informative ones.
EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning
However, these risk measures depend on the accurate estimation of extreme quantiles in the loss distribution's tail, which can be imprecise in QR-based DRL due to the rarity and extremity of tail data, as highlighted in the literature.
Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection
Polyp segmentation plays a crucial role in the early detection and diagnosis of colorectal cancer.
Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
Building on this foundation, we propose a strategy to migrate the temporal consistency in video diffusion models to the spatial-temporal consistency required for 4D generation.
ATOM: Attention Mixer for Efficient Dataset Distillation
To address these challenges in dataset distillation, we propose the ATtentiOn Mixer (ATOM) module to efficiently distill large datasets using a mixture of channel and spatial-wise attention in the feature matching process.
The Need for Speed: Pruning Transformers with One Recipe
We introduce the $\textbf{O}$ne-shot $\textbf{P}$runing $\textbf{T}$echnique for $\textbf{I}$nterchangeable $\textbf{N}$etworks ($\textbf{OPTIN}$) framework as a tool to increase the efficiency of pre-trained transformer architectures $\textit{without requiring re-training}$.
Comp4D: LLM-Guided Compositional 4D Scene Generation
Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content.
FedD2S: Personalized Data-Free Federated Knowledge Distillation
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework.
HistoSegCap: Capsules for Weakly-Supervised Semantic Segmentation of Histological Tissue Type in Whole Slide Images
Digital pathology involves converting physical tissue slides into high-resolution Whole Slide Images (WSIs), which pathologists analyze for disease-affected tissues.
NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction
Distinct from conventional Computed Tomography (CT)-based Deep Learning (DL) models, the NYCTALE performs predictions only when sufficient amount of evidence is accumulated.
A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty
In this paper, we propose an algorithm that clarifies the theoretical connection between aleatory and epistemic uncertainty, unifies aleatory and epistemic uncertainty estimation, and quantifies the combined effect of both uncertainties for a risk-sensitive exploration.
A Robust Quantile Huber Loss With Interpretable Parameter Adjustment In Distributional Reinforcement Learning
Distributional Reinforcement Learning (RL) estimates return distribution mainly by learning quantile values via minimizing the quantile Huber loss function, entailing a threshold parameter often selected heuristically or via hyperparameter search, which may not generalize well and can be suboptimal.
ProbMCL: Simple Probabilistic Contrastive Learning for Multi-label Visual Classification
We validate the effectiveness of our framework through experimentation with datasets from the computer vision and medical imaging domains.
Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization
In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer.
Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions.
DataDAM: Efficient Dataset Distillation with Attention Matching
Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic set that contains the information of a larger real dataset and ultimately achieves test accuracy equivalent to a model trained on the whole dataset.
End-to-End Supervised Multilabel Contrastive Learning
However, they fail to design an end-to-end training framework, leading to high computational complexity.
A New Probabilistic Distance Metric With Application In Gaussian Mixture Reduction
This paper presents a new distance metric to compare two continuous probability density functions.
Computational Pathology: A Survey Review and The Way Forward
Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images.
CLSA: Contrastive Learning-based Survival Analysis for Popularity Prediction in MEC Networks
Mobile Edge Caching (MEC) integrated with Deep Neural Networks (DNNs) is an innovative technology with significant potential for the future generation of wireless networks, resulting in a considerable reduction in users' latency.
Pseudo-Inverted Bottleneck Convolution for DARTS Search Space
Our proposed architecture is much less sensitive to evaluation layer count and outperforms a DARTS network with similar size significantly, at layer counts as small as 2.
Graph Federated Learning for CIoT Devices in Smart Home Applications
This paper deals with the problem of statistical and system heterogeneity in a cross-silo Federated Learning (FL) framework where there exist a limited number of Consumer Internet of Things (CIoT) devices in a smart building.
Active Inference and Reinforcement Learning: A unified inference on continuous state and action spaces under partial observability
Despite this exploratory behaviour of AIF, its usage is limited to discrete spaces due to the computational challenges associated with EFE.
ViT-CAT: Parallel Vision Transformers with Cross Attention Fusion for Popularity Prediction in MEC Networks
Followed by a Cross Attention (CA) module as the Fusion Center (FC), the proposed ViT-CAT is capable of learning the mutual information between temporal and spatial correlations, as well, resulting in improving the classification accuracy, and decreasing the model's complexity about 8 times.
Multi-Content Time-Series Popularity Prediction with Multiple-Model Transformers in MEC Networks
Most existing datadriven popularity prediction models, however, are not suitable for the coded/uncoded content placement frameworks.
Subclass Knowledge Distillation with Known Subclass Labels
In classification tasks with a small number of classes or binary detection, the amount of information transferred from the teacher to the student is restricted, thus limiting the utility of knowledge distillation.
A Kernel Method to Nonlinear Location Estimation with RSS-based Fingerprint
Given the fingerprint observed by the smartphone, the user's current location can be estimated by finding the top-k similar fingerprints from the list of fingerprints registered in the database.
AKF-SR: Adaptive Kalman Filtering-based Successor Representation
Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms.
Exploiting Explainable Metrics for Augmented SGD
In this paper, we address the following question: \textit{can we probe intermediate layers of a deep neural network to identify and quantify the learning quality of each layer?}
HistoKT: Cross Knowledge Transfer in Computational Pathology
In this paper, we take a data-centric approach to the transfer learning problem and examine the existence of generalizable knowledge between histopathological datasets.
Lung-Originated Tumor Segmentation from Computed Tomography Scan (LOTUS) Benchmark
Lung cancer is one of the deadliest cancers, and in part its effective diagnosis and treatment depend on the accurate delineation of the tumor.
Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation
The proposed MAK-TD/SR frameworks consider the continuous nature of the action-space that is associated with high dimensional multi-agent environments and exploit Kalman Temporal Difference (KTD) to address the parameter uncertainty.
TEDGE-Caching: Transformer-based Edge Caching Towards 6G Networks
As a consequence of the COVID-19 pandemic, the demand for telecommunication for remote learning/working and telemedicine has significantly increased.
Towards Robust and Automatic Hyper-Parameter Tunning
In this work, we introduce a new class of HPO method and explore how the low-rank factorization of the convolutional weights of intermediate layers of a convolutional neural network can be used to define an analytical response surface for optimizing hyper-parameters, using only training data.
P4AI: Approaching AI Ethics through Principlism
The field of computer vision is rapidly evolving, particularly in the context of new methods of neural architecture design.
NoFADE: Analyzing Diminishing Returns on CO2 Investment
Climate change continues to be a pressing issue that currently affects society at-large.
In Search of Probeable Generalization Measures
Understanding the generalization behaviour of deep neural networks is a topic of recent interest that has driven the production of many studies, notably the development and evaluation of generalization "explainability" measures that quantify model generalization ability.
CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans
Lung cancer is the leading cause of mortality from cancer worldwide and has various histologic types, among which Lung Adenocarcinoma (LUAC) has recently been the most prevalent one.
CONetV2: Efficient Auto-Channel Size Optimization for CNNs
Neural Architecture Search (NAS) has been pivotal in finding optimal network configurations for Convolution Neural Networks (CNNs).
Robust Framework for COVID-19 Identification from a Multicenter Dataset of Chest CT Scans
We showed that while our proposed model is trained on a relatively small dataset acquired from only one imaging center using a specific scanning protocol, the model performs well on heterogeneous test sets obtained by multiple scanners using different technical parameters.
On the Efficiency of Subclass Knowledge Distillation in Classification Tasks
These results show that the extra subclasses' knowledge (i. e., 0. 4656 label bits per training sample in our experiment) can provide more information about the teacher generalization, and therefore SKD can benefit from using more information to increase the student performance.
DQLEL: Deep Q-Learning for Energy-Optimized LoS/NLoS UWB Node Selection
Although UWB technology can enhance the accuracy of indoor positioning due to the use of a wide-frequency spectrum, there are key challenges ahead for its efficient implementation.
Probeable DARTS with Application to Computational Pathology
AI technology has made remarkable achievements in computational pathology (CPath), especially with the help of deep neural networks.
CONet: Channel Optimization for Convolutional Neural Networks
To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN.
COVID-Rate: An Automated Framework for Segmentation of COVID-19 Lesions from Chest CT Scans
In this context, first, the paper introduces an open access COVID-19 CT segmentation dataset containing 433 CT images from 82 patients that have been annotated by an expert radiologist.
Human-level COVID-19 Diagnosis from Low-dose CT Scans Using a Two-stage Time-distributed Capsule Network
The AI model achieves COVID-19 sensitivity of 89. 5% +\- 0. 11, CAP sensitivity of 95% +\- 0. 11, normal cases sensitivity (specificity) of 85. 7% +\- 0. 16, and accuracy of 90% +\- 0. 06.
Reconsidering CO2 emissions from Computer Vision
To address these concerns, we propose adding "enforcement" as a pillar of ethical AI and provide some recommendations for how architecture designers and broader CV community can curb the climate crisis.
Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models.
Computational Efficiency
Explainable Artificial Intelligence (XAI)
Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions.
On the Philosophical, Cognitive and Mathematical Foundations of Symbiotic Autonomous Systems (SAS)
Symbiotic Autonomous Systems (SAS) are advanced intelligent and cognitive systems exhibiting autonomous collective intelligence enabled by coherent symbiosis of human-machine interactions in hybrid societies.
Diagnosis/Prognosis of COVID-19 Images: Challenges, Opportunities, and Applications
This has resulted in a surge of interest to develop Radiomics models for analysis and interpretation of medical images.
CT-CAPS: Feature Extraction-based Automated Framework for COVID-19 Disease Identification from Chest CT Scans using Capsule Networks
Capsule Networks, on the other hand, can capture spatial relations, require smaller datasets, and have considerably fewer parameters.
COVID-FACT: A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans
The newly discovered Corona virus Disease 2019 (COVID-19) has been globally spreading and causing hundreds of thousands of deaths around the world as of its first emergence in late 2019.
COVID-CT-MD: COVID-19 Computed Tomography (CT) Scan Dataset Applicable in Machine Learning and Deep Learning
Novel Coronavirus (COVID-19) has drastically overwhelmed more than 200 countries affecting millions and claiming almost 1 million lives, since its emergence in late 2019.
MIXCAPS: A Capsule Network-based Mixture of Experts for Lung Nodule Malignancy Prediction
In particular, lung cancer is among the most common and deadliest cancers with a low 5-year survival rate.
Maximum Mutation Reinforcement Learning for Scalable Control
Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance.
Stain Style Transfer of Histopathology Images Via Structure-Preserved Generative Learning
To address the issue of color variations in histopathology images, this study proposes two stain style transfer models, SSIM-GAN and DSCSI-GAN, based on the generative adversarial networks.
All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling
Recent advances in high refresh rate displays as well as the increased interest in high rate of slow motion and frame up-conversion fuel the demand for efficient and cost-effective multi-frame video interpolation solutions.
FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology
Out-of-focus microscopy lens in digital pathology is a critical bottleneck in high-throughput Whole Slide Image (WSI) scanning platforms, for which pixel-level automated Focus Quality Assessment (FQA) methods are highly desirable to help significantly accelerate the clinical workflows.
AdaS: Adaptive Scheduling of Stochastic Gradients
The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures.
MM-KTD: Multiple Model Kalman Temporal Differences for Reinforcement Learning
As a result, the proposed MM-KTD framework can learn the optimal policy with significantly reduced number of samples as compared to its DNN-based counterparts.
How Much Off-The-Shelf Knowledge Is Transferable From Natural Images To Pathology Images?
Particularly, compared to the performance baseline obtained by random-weight model, though transferability of off-the-shelf representations from deep layers heavily depend on specific pathology image sets, the general representation generated by early layers does convey transferred knowledge in various image classification applications.
COVID-CAPS: A Capsule Network-based Framework for Identification of COVID-19 cases from X-ray Images
Pre-training with a dataset of similar nature further improved accuracy to 98. 3% and specificity to 98. 6%.
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
Our experiments indicate that histopathology and satellite images present a different set of problems for weakly-supervised semantic segmentation than natural scene images, such as ambiguous boundaries and class co-occurrence.
Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder
We apply the proposed method to a public breast cancer image set.
Focus Quality Assessment of High-Throughput Whole Slide Imaging in Digital Pathology
We also extend our method to generate a local slide-level focus quality heatmap, which can be used for automated slide quality control, and demonstrate the utility of our method for clinical scan quality control by comparison with subjective slide quality scores.
Capsule Networks for Brain Tumor Classification based on MRI Images and Course Tumor Boundaries
According to official statistics, cancer is considered as the second leading cause of human fatalities.
Convolutional Deblurring for Natural Imaging
In this paper, we propose a novel design of image deblurring in the form of one-shot convolution filtering that can directly convolve with naturally blurred images for restoration.
From Hand-Crafted to Deep Learning-based Cancer Radiomics: Challenges and Opportunities
Recent advancements in signal processing and machine learning coupled with developments of electronic medical record keeping in hospitals and the availability of extensive set of medical images through internal/external communication systems, have resulted in a recent surge of significant interest in "Radiomics".
Improved Explainability of Capsule Networks: Relevance Path by Agreement
Recent advancements in signal processing and machine learning domains have resulted in an extensive surge of interest in deep learning models due to their unprecedented performance and high accuracy for different and challenging problems of significant engineering importance.
Brain Tumor Type Classification via Capsule Networks
Brain tumor is considered as one of the deadliest and most common form of cancer both in children and in adults.
High-Accuracy Total Variation for Compressed Video Sensing
Numerous total variation (TV) regularizers, engaged in image restoration problem, encode the gradients by means of simple $[-1, 1]$ FIR filter.
