发表机构
Université Paris-Saclay; CentraleSupélec; Gustave Roussy; INSERM; IHU PRISM; MICS Laboratory（巴黎萨克雷大学; 中央理工-高等电力学院; 古斯塔夫·鲁西癌症中心; 法国国家健康与医学研究院; PRISM大学医院研究所; MICS实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CAR-MIL框架，通过反事实注意力正则化引导MIL中的注意力学习，提升注意力可靠性并保持分类性能，在合成基准和五个病理数据集上验证了有效性。
AI 中文摘要
多实例学习（MIL）被广泛用于弱监督学习，尤其是在数字病理学中，因为细粒度标注成本高昂。大多数MIL方法通过注意力机制聚合实例特征。然而，注意力权重并不总是忠实地反映实例的重要性，可能聚焦于虚假相关的区域。在这项工作中，我们提出了CAR-MIL，一个通过受反事实解释启发的反事实注意力正则化目标来显式引导注意力学习的框架。基于标准的注意力MIL架构，我们的方法引入了一个轻量级的反事实注意力分支，该分支被训练为产生替代预测，同时保持与事实注意力分布接近。这鼓励预测变化源于最小化、结构化的注意力重新分配，从而实现更具信息性的证据分配。由此产生的事实和反事实注意力图捕获互补证据：前者突出支持预测的区域，而后者揭示重新加权会挑战预测的区域。我们在具有实例级真实标签的合成MIL基准上评估了我们的方法，以对注意力行为进行受控分析，并在四个任务的五个数字病理学数据集上进行了评估。CAR-MIL保持了有竞争力的分类性能，在更具挑战性的任务上取得了最大增益，同时提高了注意力可靠性，证明了将反事实可解释性推理整合到注意力学习中的益处。代码可在以下网址获取：此https URL。
英文摘要
Multiple Instance Learning (MIL) is widely used for weakly supervised learning, particularly in digital pathology, where fine-grained annotations are costly. Most MIL methods aggregate instance features via attention mechanisms. However, attention weights do not always faithfully reflect instance importance and may focus on spuriously correlated regions. In this work, we propose CAR-MIL, a framework that explicitly guides attention learning through a counterfactual attention regularization objective inspired by counterfactual explanations. Built on a standard attention-based MIL architecture, our approach introduces a lightweight counterfactual attention branch trained to produce an alternative prediction while remaining close to the factual attention distribution. This encourages prediction changes to arise from minimal, structured redistributions of attention, leading to more informative evidence allocation. The resulting factual and counterfactual attention maps capture complementary evidence: the former highlights regions supporting the prediction, while the latter reveals regions whose reweighting would challenge it. We evaluate our method on synthetic MIL benchmarks with instance-level ground truth enabling controlled analysis of attention behavior and on five digital pathology datasets across four tasks. CAR-MIL maintains competitive classification performance, with the largest gains observed on more challenging tasks, while improving attention reliability, demonstrating the benefits of integrating counterfactual explainability reasoning into attention learning. Code is available at: https://github.com/ImaneCR/CAR-MIL/.
CommentsAccepted at ECCV 2026
