AI RESEARCH
ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging
arXiv CS.CV
•
ArXi:2603.06658v1 Announce Type: new Attention-based multiple instance learning (MIL) has emerged as a powerful framework for whole slide image (WSI) diagnosis, leveraging attention to aggregate instance-level features into bag-level predictions. Despite this success, we find that such methods exhibit a new failure mode: unstable attention dynamics. Across four representative attention-based MIL methods and two public WSI datasets, we observe that attention distributions oscillate across epochs rather than converging to a consistent pattern, degrading performance.