Picture for Bilal Alsallakh

Bilal Alsallakh

On Symmetries in Convolutional Weights

Add code
Mar 24, 2025
Viaarxiv icon

Bias Mitigation Framework for Intersectional Subgroups in Neural Networks

Add code
Dec 26, 2022
Viaarxiv icon

Prescriptive and Descriptive Approaches to Machine-Learning Transparency

Add code
Apr 27, 2022
Figure 1 for Prescriptive and Descriptive Approaches to Machine-Learning Transparency
Figure 2 for Prescriptive and Descriptive Approaches to Machine-Learning Transparency
Viaarxiv icon

A Tour of Visualization Techniques for Computer Vision Datasets

Add code
Apr 19, 2022
Figure 1 for A Tour of Visualization Techniques for Computer Vision Datasets
Figure 2 for A Tour of Visualization Techniques for Computer Vision Datasets
Figure 3 for A Tour of Visualization Techniques for Computer Vision Datasets
Figure 4 for A Tour of Visualization Techniques for Computer Vision Datasets
Viaarxiv icon

Investigating sanity checks for saliency maps with image and text classification

Add code
Jun 08, 2021
Figure 1 for Investigating sanity checks for saliency maps with image and text classification
Figure 2 for Investigating sanity checks for saliency maps with image and text classification
Figure 3 for Investigating sanity checks for saliency maps with image and text classification
Figure 4 for Investigating sanity checks for saliency maps with image and text classification
Viaarxiv icon

Investigating Saturation Effects in Integrated Gradients

Add code
Oct 23, 2020
Figure 1 for Investigating Saturation Effects in Integrated Gradients
Figure 2 for Investigating Saturation Effects in Integrated Gradients
Figure 3 for Investigating Saturation Effects in Integrated Gradients
Figure 4 for Investigating Saturation Effects in Integrated Gradients
Viaarxiv icon

Mind the Pad -- CNNs can Develop Blind Spots

Add code
Oct 05, 2020
Figure 1 for Mind the Pad -- CNNs can Develop Blind Spots
Figure 2 for Mind the Pad -- CNNs can Develop Blind Spots
Figure 3 for Mind the Pad -- CNNs can Develop Blind Spots
Figure 4 for Mind the Pad -- CNNs can Develop Blind Spots
Viaarxiv icon

Captum: A unified and generic model interpretability library for PyTorch

Add code
Sep 16, 2020
Figure 1 for Captum: A unified and generic model interpretability library for PyTorch
Figure 2 for Captum: A unified and generic model interpretability library for PyTorch
Figure 3 for Captum: A unified and generic model interpretability library for PyTorch
Figure 4 for Captum: A unified and generic model interpretability library for PyTorch
Viaarxiv icon

Visualizing Classification Structure in Deep Neural Networks

Add code
Jul 12, 2020
Figure 1 for Visualizing Classification Structure in Deep Neural Networks
Figure 2 for Visualizing Classification Structure in Deep Neural Networks
Figure 3 for Visualizing Classification Structure in Deep Neural Networks
Figure 4 for Visualizing Classification Structure in Deep Neural Networks
Viaarxiv icon

Prediction Scores as a Window into Classifier Behavior

Add code
Nov 18, 2017
Figure 1 for Prediction Scores as a Window into Classifier Behavior
Figure 2 for Prediction Scores as a Window into Classifier Behavior
Viaarxiv icon