用差分调试找视觉模型最精简的决策依据，解释更精准。
DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging
- 基于差分调试，自动筛选最小必要特征组合
- 移除任一特征即改变预测，证明其必要性
- 适合需要高可信度解释的场景，如医疗影像
我们提出一种无梯度的框架DD-CAM，用于识别视觉模型中最小、充分且决策不变的解释。该方法通过隔离代表单元的最小子集，使其联合激活足以维持原预测结果（即移除任意一个单元都会改变预测）。为高效定位此类最小充分子集，我们借鉴软件调试中的差分调试策略，并根据分类器头部单元间是否存在交互，调整搜索策略：对无交互模型测试单个单元，对有交互模型测试单元组合。最终生成仅突出最关键特征的最小化、预测保持性显著图。实验表明，该方法在忠实度和定位精度上均优于现有基于CAM的先进方法。
原文摘要 · Abstract (English)
We introduce a gradient-free framework for identifying minimal, sufficient, and decision-preserving explanations in vision models by isolating the smallest subset of representational units whose joint activation preserves predictions. Unlike existing approaches that aggregate all units, often leading to cluttered saliency maps, our approach, DD-CAM, identifies a 1-minimal subset whose joint activation suffices to preserve the prediction (i.e., removing any unit from the subset alters the prediction). To efficiently isolate minimal sufficient subsets, we adapt delta debugging, a systematic reduction strategy from software debugging, and configure its search strategy based on unit interactions in the classifier head: testing individual units for models with non-interacting units and testing unit combinations for models in which unit interactions exist. We then generate minimal, prediction-preserving saliency maps that highlight only the most essential features. Our experimental evaluation demonstrates that our approach can produce more faithful explanations and achieve higher localization accuracy than the state-of-the-art CAM-based approaches.
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。