| Title: |
Two-Stage Holistic and Contrastive Explanation of Image Classification |
| Authors: |
Xie, Weiyan; Li, Xiao-Hui; Lin, Zhi; Poon, Leonard K. M.; Cao, Caleb Chen; Zhang, Nevin L. |
| Publication Year: |
2023 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Computer Vision and Pattern Recognition |
| Description: |
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.; Comment: To appear at UAI 2023 |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2306.06339 |
| Accession Number: |
edsarx.2306.06339 |
| Database: |
arXiv |