A Learning Paradigm for Interpretable Gradients

arXiv:2404.15024v1 Announce Type: cross
Abstract: This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation. However, it is well understood that gradients are noisy and alternatives like guided backpropagation have been proposed to obtain better visualization at inference. In this work, we present a novel training approach to improve the quality of gradients for interpretability. In particular, we …

abstract arxiv backpropagation class cs.cv cs.lg gradient however information interpretability maps networks paper paradigm studies through type variants