SOURCE-LINKED INTELLIGENCE

CAR-MIL: Counterfactual Attention Regularization for Multiple Instance Learning

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

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,

Read original source ↗ Open in workspace

recordType

paper

region

Global