# Two-Stage Holistic and Contrastive Explanation of Image Classification

Source: [Two-Stage Holistic and Contrastive Explanation of Image Classification](<https://www.sota2.com/research/paper/68fa6fc01e209131cea473b1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:24:25.429Z

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

Published: 2023-06-10T04:22:13.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.06339>)

[PDF](<https://arxiv.org/pdf/2306.06339.pdf>)