改进了图像解释的特征归因方法，让结果更准确且高效。
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)
- 用层次化分组替代传统分割，更好捕捉像素语义关系。
- 在图像和表格数据上，归因精度和可解释性均优于现有方法。
- 适合关注解释结果语义合理性的研究人员或工程师。
基于Shapley值的解释方法在可解释人工智能中已成为基础，通过合作博弈论提供理论支持的特征重要性评估。然而，在视觉任务中，特征（即像素）常具有强空间与语义依赖，独立性假设不成立。现代SHAP方法引入了Owen值——一种层次化的Shapley值推广，支持分组归因。但其效果高度依赖特征分组定义。我们发现常见分割方式（如轴对齐或SLIC）违反关键一致性性质，提出满足$T$-性质的新分割方法，确保跨层级语义一致。该层次结构支持计算剪枝，提升归因精度与可解释性。在图像和表格数据集上的实验表明，O-Shap在归因精度、语义连贯性和运行效率上均优于基线变体，尤其在结构重要时表现更优。
原文摘要 · Abstract (English)
Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game theory. However, in practice, particularly in vision tasks, the assumption of feature independence breaks down, as features (i.e., pixels) often exhibit strong spatial and semantic dependencies. To address this, modern SHAP implementations now include the Owen value, a hierarchical generalization of the Shapley value that supports group attributions. While the Owen value preserves the foundations of Shapley values, its effectiveness critically depends on how feature groups are defined. We show that commonly used segmentations (e.g., axis-aligned or SLIC) violate key consistency properties, and propose a new segmentation approach that satisfies the $T$-property to ensure semantic alignment across hierarchy levels. This hierarchy enables computational pruning while improving attribution accuracy and interpretability. Experiments on image and tabular datasets demonstrate that O-Shap outperforms baseline SHAP variants in attribution precision, semantic coherence, and runtime efficiency, especially when structure matters.
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。