research
∙
07/06/2023
A Vulnerability of Attribution Methods Using Pre-Softmax Scores
We discuss a vulnerability involving a category of attribution methods u...
share
research
∙
06/22/2023
Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?
Gradient based attribution methods for neural networks working as classi...
research
∙
05/22/2022
Visual Explanations from Deep Networks via Riemann-Stieltjes Integrated Gradient-based Localization
Neural networks are becoming increasingly better at tasks that involve c...
research
∙
05/22/2022
Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients
The Grad-CAM algorithm provides a way to identify what parts of an image...
research
∙
04/13/2022
Baseline Computation for Attribution Methods Based on Interpolated Inputs
We discuss a way to find a well behaved baseline for attribution methods...
research
∙
03/25/2021