图像解释质量受分割与平滑影响更大，而非扰动方法选择。
Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations
- 通过组合不同分割、平滑和归因计算方式评估解释效果。
- 分割与像素级归因显著影响解释质量，归因计算影响较小。
- 适合关注解释结果可信度的模型可解释性研究者参考。
基于扰动的后处理图像解释方法广泛用于解释图像预测模型，通过扰动输入部分来衡量其对输出的影响。由于仅需输入和输出，该类方法可适用于任意模型，是解释黑箱模型的常用手段。尽管已有多种方法被提出并相互比较，但其性能差异主要由哪些参数决定仍不明确。本文以随机输入采样解释法（RISE）为基准，评估了掩码采样、分割技术、平滑处理、归因计算方式，以及逐段或逐像素归因等多种组合，采用代理指标进行分析。结果表明，归因计算方式虽常被关注，但对结果影响甚微；而分割策略和像素级归因则显著影响解释质量。相关代码与数据已公开：https://github.com/guspih/post-hoc-image-perturbation 及 https://bit.ly/smooth-mask-perturbation。
原文摘要 · Abstract (English)
Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models. These methods perturb parts of the input to measure how those parts affect the output. Since the methods only require the input and output, they can be applied to any model, making them a popular choice to explain black-box models. While many different methods exist and have been compared with one another, it remains poorly understood which parameters of the different methods are responsible for their varying performance. This work uses the Randomized Input Sampling for Explanations (RISE) method as a baseline to evaluate many combinations of mask sampling, segmentation techniques, smoothing, attribution calculation, and per-segment or per-pixel attribution, using a proxy metric. The results show that attribution calculation, which is frequently the focus of other works, has little impact on the results. Conversely, segmentation and per-pixel attribution, rarely examined parameters, have a significant impact. The implementation of and data gathered in this work are available online: https://github.com/guspih/post-hoc-image-perturbation and https://bit.ly/smooth-mask-perturbation.
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。