少即是多：通过子模子集选择获得更少的可解释区域
Less is More: Fewer Interpretable Region via Submodular Subset Selection
AI总结：
本文将图像归因重构为子模子集选择问题，通过新型子模函数与四项约束选择更少且更准确的可解释区域，显著提升正确及错误预测样本的归因表现。
摘要：
图像归因算法旨在识别与模型决策高度相关的重要区域。尽管现有归因解决方案能够有效地为目标元素分配重要性，但它们仍面临以下挑战：1）现有归因方法会生成不准确的小区域，从而误导正确归因的方向；2）对于预测错误的样本，模型无法产生良好的归因结果。为应对上述挑战，本文将上述图像归因问题重新建模为子模子集选择问题，旨在利用更少的区域增强模型可解释性。为解决对局部区域关注不足的问题，我们构建了一种新颖的子模函数，以发现更准确的小型解释区域。为增强对所有样本的归因效果，我们还对子区域的选择施加了四种不同约束，即置信度、有效性、一致性和协作分数，用于评估各种子集的重要性。此外，我们的理论分析证实所提出的函数实际上具有子模性。大量实验表明，所提方法在两个人脸数据集（Celeb-A 和 VGG-Face2）以及一个细粒度数据集（CUB-200-2011）上优于 SOTA 方法。对于预测正确的样本，所提方法相对于 HSIC-Attribution 将 Deletion 和 Insertion 分数平均提升了 4.9% 和 2.5%。对于预测错误的样本，我们的方法在平均最高置信度和 Insertion 分数上分别比 HSIC-Attribution 算法取得 81.0% 和 18.4% 的提升。代码已发布于 https://github.com/RuoyuChen10/SMDL-Attribution。
英文摘要：
Image attribution algorithms aim to identify important regions that are highly relevant to model decisions. Although existing attribution solutions can effectively assign importance to target elements, they still face the following challenges: 1) existing attribution methods generate inaccurate small regions thus misleading the direction of correct attribution, and 2) the model cannot produce good attribution results for samples with wrong predictions. To address the above challenges, this paper re-models the above image attribution problem as a submodular subset selection problem, aiming to enhance model interpretability using fewer regions. To address the lack of attention to local regions, we construct a novel submodular function to discover more accurate small interpretation regions. To enhance the attribution effect for all samples, we also impose four different constraints on the selection of sub-regions, i.e., confidence, effectiveness, consistency, and collaboration scores, to assess the importance of various subsets. Moreover, our theoretical analysis substantiates that the proposed function is in fact submodular. Extensive experiments show that the proposed method outperforms SOTA methods on two face datasets (Celeb-A and VGG-Face2) and one fine-grained dataset (CUB-200-2011). For correctly predicted samples, the proposed method improves the Deletion and Insertion scores with an average of 4.9% and 2.5% gain relative to HSIC-Attribution. For incorrectly predicted samples, our method achieves gains of 81.0% and 18.4% compared to the HSIC-Attribution algorithm in the average highest confidence and Insertion score respectively. The code is released at https://github.com/RuoyuChen10/SMDL-Attribution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
