发表机构
Julius-Maximilians-Universität Würzburg; University of Groningen（维尔茨堡大学; 格罗宁根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器学习模型行为难解释问题，通过调整LIME，利用生成式图像修复改进基于扰动的图像解释，获得更逼真样本，提升了解释质量。
AI 中文摘要
随着先进机器学习模型的复杂性增加，其行为愈发难以解释，推动了可解释人工智能（XAI）领域的快速发展。基于扰动的方法在众多XAI方法中起主要作用，传统扰动技术会生成不现实的样本并留下可见伪影，影响解释质量。本文调整了广泛使用的基于扰动的方法LIME，并展示生成式图像修复如何改进基于扰动的图像解释，实现更符合原始数据分布的逼真扰动样本并提高解释质量。
英文摘要
The increasing complexity of state-of-the-art machine learning models has made their behavior progressively harder to interpret, spurring rapid advancements in the field of eXplainable Artificial Intelligence (XAI). Among many methods proposed, perturbation-based approaches play a major role. By systematically altering (perturbing) input features, these approaches measure the impact on the model's predictions. For image data, traditional perturbation techniques, often involve replacing pixel values e.g., with a pre-defined color. However, such approaches, but also more refined deterministic techniques, generate unrealistic out-of-distribution samples and often leave visible artifacts, which can mislead the model and compromise explanation quality. In this work, we adjust LIME, a widely used perturbation-based method, to demonstrate how generative inpainting can improve perturbation-based explanations for images. We achieve photorealistic perturbed samples that align better with the original data distribution and enhance explanation quality.
CommentsPreprint accepted at XAIE4 (ICPR 2026). 15 pages, 5 figures, 4 tables. Code available at: https://github.com/jo01123/LILI and https://github.com/m-chaves/LIME
