FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision

arXiv:2312.05975v2 Announce Type: replace-cross
Abstract: Explainability is an aspect of modern AI that is vital for impact and usability in the real world. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network (CNN) based models. Existing methods of explaining CNN predictions are mostly based on Gradient-weighted Class Activation Maps (Grad-CAM) and solely focus on a single target class. We show that from the point of the …

abstract arxiv cnn computer computer vision convolutional neural network cs.ai cs.cv cs.lg explainability explainable ai impact modern modern ai network neural network paper predictions type usability vision vision models vital world