用生成式修复技术让图像扰动更真实，提升AI解释可信度
Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations
- 用生成模型修复被遮蔽区域，生成更符合真实分布的图像扰动
- 相比传统涂色方法，新方法显著减少伪影，解释结果更稳定可靠
- 适合需要高可信度视觉解释的医疗、自动驾驶等场景
随着先进机器学习模型复杂度不断提升，其行为日益难以解释，推动了可解释人工智能（XAI）的快速发展。其中，基于扰动的方法占据重要地位：通过系统性地改变输入特征并观察模型输出变化来分析影响。对于图像数据，传统扰动方法通常用固定颜色覆盖像素，而更精细的确定性方法也常产生分布外的不真实样本并留下明显痕迹，可能误导模型评估，降低解释质量。本文改进了广泛使用的LIME方法，引入生成式图像修复技术，实现更逼真的扰动样本生成。所生成的图像与原始数据分布更加一致，显著提升了视觉解释的准确性与可信度。
原文摘要 · Abstract (English)
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.
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。