UAI 2023poster2 citations

Two-stage holistic and contrastive explanation of image classification

Weiyan Xie, Xiao-Hui Li, Zhi Lin, Leonard K. M. Poon, Caleb Chen Cao, Nevin L. Zhang

Abstract

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.

BibTeX
@InProceedings{pmlr-v216-xie23a,
  title = 	 {Two-stage holistic and contrastive explanation of image classification},
  author =       {Xie, Weiyan and Li, Xiao-Hui and Lin, Zhi and Poon, Leonard K. M. and Cao, Caleb Chen and Zhang, Nevin L.},
  booktitle = 	 {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {2335--2345},
  year = 	 {2023},
  editor = 	 {Evans, Robin J. and Shpitser, Ilya},
  volume = 	 {216},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {31 Jul--04 Aug},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v216/xie23a/xie23a.pdf},
  url = 	 {https://proceedings.mlr.press/v216/xie23a.html},
  abstract = 	 {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.}
}