activity
20172021
most citedExplaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks

11 citations · 27 across the 8 of their papers we have counts for

collaborators

9 papers

cs.LG2021

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

Saad Abbasi, Mohammad Javad Shafiee, Ellick Chan +1

The fine-grained relationship between form and function with respect to deep neural network architecture design and hardware-specific acceleration is one area that is not well stud…

cs.LG20212 cited

Residual Error: a New Performance Measure for Adversarial Robustness

Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg +2

Despite the significant advances in deep learning over the past decade, a major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversar…

cs.CV2021

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

Xiaoyu Wen, Mahmoud Famouri, Andrew Hryniowski +1

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

cs.CV20215 cited

Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics

Stone Yun, Alexander Wong

As the "Mobile AI" revolution continues to grow, so does the need to understand the behaviour of edge-deployed deep neural networks. In particular, MobileNets are the go-to family…

cs.LG20191 cited

Beyond Explainability: Leveraging Interpretability for Improved Adversarial Learning

Devinder Kumar, Ibrahim Ben-Daya, Kanav Vats +3

In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability. In particular, this study puts forward a novel strategy for leve…

cs.CV20196 cited

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

Vignesh Sankar, Devinder Kumar, David A. Clausi +2

Objective: Lung cancer is the leading cause of cancer-related death worldwide. Computer-aided diagnosis (CAD) systems have shown significant promise in recent years for facilitatin…