Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape

arXiv:2403.06013v1 Announce Type: new
Abstract: This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated. Through a novel evaluation approach leveraging clustering for efficient assessment of explanation robustness, we demonstrate that enhancing explanation robustness does not necessarily flatten the input loss landscape with respect to explanation loss - contrary to flattened loss landscapes indicating better classification robustness. To deeply investigate this contradiction, …

abstract analysis arxiv assessment belief classification clustering cs.cv cs.lg deep learning evaluation image landscape loss novel paper robustness systems through type