GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

Abstract

We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network layers, GAM offers improved visual explanations, when compared to existing alternatives. The algorithmic advantages of GAM are explained in detail, and validated empirically, where it is shown that GAM outperforms its alternatives across various tasks and datasets.

arXiv commentCIKM 2021

References in corpus (8)

• Striving for Simplicity: The All Convolutional Net
• Deep Learning Face Representation by Joint Identification-Verification
• Understanding Neural Networks Through Deep Visualization
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Sanity Checks for Saliency Maps
• Asymmetric Loss For Multi-Label Classification
• Visualizing and Comparing Convolutional Neural Networks
• Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps

Cited by in corpus (1)

• Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps