用感知几何路径生成更自然的反事实解释，避免模型误判。
Counterfactual Explanations on Robust Perceptual Geodesics
- 基于鲁棒视觉特征构建感知黎曼度量，引导反事实路径
- 在三个数据集上优于基线，实现平滑且语义一致的推理变化
- 适合研究可解释AI与模型脆弱性分析的人士
针对反事实解释中的隐含歧义问题，现有方法因采用平坦或错位的几何结构，常导致离流形伪影、语义漂移或对抗性崩溃。本文提出感知反事实测地线（PCG），通过鲁棒视觉特征诱导的感知黎曼度量，在流形上追踪测地线路径，使扰动更贴近人类感知，抑制脆弱方向。在三个视觉数据集上的实验表明，PCG显著优于基线方法，并揭示了标准度量下隐藏的模型失效模式。
原文摘要 · Abstract (English)
Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.'s objective: the choice of distance metric dictates whether perturbations are meaningful or adversarial. Existing approaches adopt flat or misaligned geometries, leading to off-manifold artifacts, semantic drift, or adversarial collapse. We introduce Perceptual Counterfactual Geodesics (PCG), a method that constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric induced from robust vision features. This geometry aligns with human perception and penalizes brittle directions, enabling smooth, on-manifold, semantically valid transitions. Experiments on three vision datasets show that PCG outperforms baselines and reveals failure modes hidden under standard metrics.
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。