AI RESEARCH
DiffGradCAM: A Universal Class Activation Map Resistant to Adversarial Training
arXiv CS.LG
•
ArXi:2506.08514v3 Announce Type: replace Class Activation Mapping (CAM) and its gradient-based variants (e.g., GradCAM) have become standard tools for explaining Convolutional Neural Network (CNN) predictions. However, these approaches typically focus on individual logits, while for neural networks using softmax, the class membership probability estimates depend \textit{only} on the \textit{differences} between logits, not on their absolute values.