CVJun 15, 2021
Explaining decision of model from its prediction
arXiv:2106.08366v1
AI Analysis
This is an incremental survey for researchers in interpretable machine learning.
The paper surveys various visual explanation methods for model decisions, including CAM, Grad-CAM, and others, and compares their results.
This document summarizes different visual explanations methods such as CAM, Grad-CAM, Localization using Multiple Instance Learning - Saliency-based methods, Saliency-driven Class-Impressions, Muting pixels in input image - Adversarial methods and Activation visualization, Convolution filter visualization - Feature-based methods. We have also shown the results produced by different methods and a comparison between CAM, GradCAM, and Guided Backpropagation.