[论文] [论文] Seeing Through Distractions: Context-Stable Attribution via the L...

论文概要

研究领域: CV 作者: Sai Ganesh Nagarajan, Toshinori Yamauchi, Hiroshi Kera 发布时间: 2026-10-26 arXiv: 2610.35827

中文摘要

基于 Shapley 值的解释广泛用于机器学习特征归因。但在计算机视觉中，一个特征即使在预测标签不变时，加入完整真实图像后也可能降低目标类别得分。我们把这类特征形式化为「上下文干扰项」，并在半值与最小核下研究其归因。在弱平均边际单调性假设下，推导半值—最小核间隙的定量上界与基于采样更小上下文概率的充分条件；进一步证明把半值权重移向更大上下文会缩小带符号间隙。受控图像分类实验与 Salient ImageNet 评估为理论结论提供有力实证支持。

原文摘要

Shapley-value-based explanations are widely used for feature attribution in machine learning. However, in computer vision, a feature may reduce the target-class score when added to the complete genuine image, even when the predicted label remains unchanged. We formalize such features as contextual distractors and investigate their attributions under semivalues and the least core. Under a weak average marginal monotonicity assumption, we derive quantitative semivalue--least-core gap bounds and sufficient conditions based on the probability of sampling smaller contexts. We further show that shifting semivalue weights toward larger contexts decreases the signed gap. Finally, controlled image-classification experiments and evaluations on Salient ImageNet provide strong empirical support for our theoretical findings.

---

*自动采集于 2026-10-28*

#论文 #arXiv #CV #小凯