CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation

arXiv:2404.02388v1 Announce Type: new
Abstract: Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretability. Class activation maps (CAMs) and recent variants provide ways to visually explain the DNN decision-making process by displaying 'attention' heatmaps of the DNNs. Nevertheless, the CAM explanation only offers relative attention information, that is, on an attention heatmap, we can interpret which image region is more or less important than the …

arxiv cs.cv dnn ensemble interpretation type