Two-stage holistic and contrastive explanation of image classification

Weiyan XIE, Xiao-Hui LI, Zhi LIN, Kin Man POON, Caleb Chen CAO, Nevin L. ZHANG

Research output: Contribution to journalArticlespeer-review


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 Copyright © 2023 Authors.

Original languageEnglish
Pages (from-to)2335-2345
JournalProceedings of Machine Learning Research
Publication statusPublished - 2023


Xie, W., Li, X.-H., Lin, Z., Poon, L. K. M., Cao, C. C., & Zhang, N. L. (2023). Two-stage holistic and contrastive explanation of image classification. Proceedings of Machine Learning Research, 216, 2335-2345.


Dive into the research topics of 'Two-stage holistic and contrastive explanation of image classification'. Together they form a unique fingerprint.