对比解释模型选某类而非其他类的原因，提升可复现性。
Reproducibility review of "Why Not Other Classes": Towards Class-Contrastive Back-Propagation Explanations
- 从softmax后反向传播，对比不同类别选择依据。
- 在XGradCAM、FullGrad和ViT上验证方法泛化能力良好。
- 开源代码并指出原论文方法描述不清、公式错误问题。
《Why Not Other Classes?》提出一种对比解释方法，通过在softmax层后进行反向传播，揭示神经网络图像分类器为何选择某一类别而非其他类别。本文对原工作进行了复现，并扩展至XGradCAM、FullGrad及视觉变换器（Vision Transformers）以评估其泛化性能。复现结果与原文基本一致，仅热力图可视化存在差异，无法完全复现。方法在多种模型和解释技术上表现良好，证明具备较强通用性。同时发现原论文存在方法描述不完整、公式错误等问题，严重影响可复现性。为此，本文开源全部代码，助力后续研究。
原文摘要 · Abstract (English)
"Why Not Other Classes?": Towards Class-Contrastive Back-Propagation Explanations (Wang & Wang, 2022) provides a method for contrastively explaining why a certain class in a neural network image classifier is chosen above others. This method consists of using back-propagation-based explanation methods from after the softmax layer rather than before. Our work consists of reproducing the work in the original paper. We also provide extensions to the paper by evaluating the method on XGradCAM, FullGrad, and Vision Transformers to evaluate its generalization capabilities. The reproductions show similar results as the original paper, with the only difference being the visualization of heatmaps which could not be reproduced to look similar. The generalization seems to be generally good, with implementations working for Vision Transformers and alternative back-propagation methods. We also show that the original paper suffers from issues such as a lack of detail in the method and an erroneous equation which makes reproducibility difficult. To remedy this we provide an open-source repository containing all code used for this project.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。