使分类解释忠实于置信度分数
Making the Classification Explanation Faithful to the Confidence Score
提出一种黑盒解释方法 MHE，通过 Metropolis-Hastings 采样生成与分类器置信度分数高度一致的图像区域解释，并利用已有有效样本提升采样效率；可直接用于分析和调试视觉分类模型（如 ResNet、ViT、CLIP）的决策依据。
原文依据 MHE enhances the fidelity of explanations by ensuring that the explained regions closely align with the original confidence score, sampling instances that best match the classifier's confidence.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度神经网络（DNN）已经彻底改变了许多行业，但其决策过程在很大程度上仍然不透明。大多数现有解释方法可视化影响分类器决策的图像区域的重要性，但它们主要关注识别具有正贡献的区域，往往忽略了具有负影响的区域。在本文中，我们引入了一种新颖的黑盒解释方法——Metropolis-Hastings解释器（MHE），旨在提供置信度忠实的解释。MHE通过确保所解释的区域与原始置信度分数紧密对齐来提高解释的保真度，采样最匹配分类器置信度的实例。此外，MHE通过利用现有有效样本探索更多潜在有效样本来提高采样效率，减少计算开销。为了提高解释的清晰度，在其他因素相等时，MHE优先选择面积较小的有效样本，从而减少解释区域。在MHE框架的基础上，我们提出了两个扩展：MHE-e，仅关注具有正贡献的区域；以及MHE-pro，通过整合多尺度信息来细化解释质量。MHE-pro逐步处理区域，优化采样效率和解释质量。实验结果表明，MHE在ResNet50、VGG16、ViT、DINO和CLIP等各种模型上，在ImageNet、CUB-200-2011和VOC2012等数据集上提供了优越且稳定的解释质量，提供的解释紧密接近原始分类置信度。
英文原文摘要 1658 字符
Deep Neural Networks (DNNs) have revolutionized numerous industries, yet their decision-making processes remain largely opaque. Most existing explanation methods visualize the importance of image regions that influence a classifier's decisions, but they predominantly focus on identifying regions with positive contributions, often overlooking those with negative impacts. In this paper, we introduce a novel black-box explanation method, the Metropolis-Hastings Explainer (MHE), designed to provide confidence-faithful explanations. MHE enhances the fidelity of explanations by ensuring that the explained regions closely align with the original confidence score, sampling instances that best match the classifier's confidence. Furthermore, MHE improves sampling efficiency by utilizing existing valid samples to explore more potential valid ones, reducing computational overhead. To enhance the clarity of explanations, MHE prioritizes valid samples with smaller areas when other factors are equal, thereby reducing the explanation area. Building upon the MHE framework, we propose two extensions: MHE-e, which focuses exclusively on regions with positive contributions, and MHE-pro, which refines explanation quality by integrating multi-scale information. MHE-pro progressively regions, optimizing both sampling efficiency and explanation quality. Experimental results demonstrate that MHE delivers superior and stable explanation quality across various models, including ResNet50, VGG16, ViT, DINO, and CLIP, on datasets such as ImageNet, CUB-200-2011, and VOC2012, providing explanations that closely approximate the original classification confidence.