The need to explain the output of a deep neural network classifier is now widely recognized. While previous methods typically explain a single class in the output, we advocate explaining the whole output, which is a probability distribution over multiple classes. A whole-output explanation can help a human user gain an overall understanding of model behaviour instead of only one aspect of it. It can also provide a natural framework where one can examine the evidence used to discriminate between competing classes, and thereby obtain contrastive explanations. In this paper, we propose a contrastive whole-output explanation (CWOX) method for image classification, and evaluate it using quantitative metrics and through human subject studies. The source code of CWOX is available at https://github.com/vaynexie/CWOX.
@article{arxiv.2306.06339,
title = {Two-Stage Holistic and Contrastive Explanation of Image Classification},
author = {Weiyan Xie and Xiao-Hui Li and Zhi Lin and Leonard K. M. Poon and Caleb Chen Cao and Nevin L. Zhang},
journal= {arXiv preprint arXiv:2306.06339},
year = {2023}
}