Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging

About

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. This instability adds to two previously reported challenges: overfitting and over-concentrated attention distribution. To simultaneously overcome these three limitations, we introduce attention-stabilized multiple instance learning (ASMIL), a novel unified framework. ASMIL uses an anchor model to stabilize attention, replaces softmax with a normalized sigmoid function in the anchor to prevent over-concentration, and applies token random dropping to mitigate overfitting. Extensive experiments demonstrate that ASMIL achieves up to a 6.49\% F1 score improvement over state-of-the-art methods. Moreover, integrating the anchor model and normalized sigmoid into existing attention-based MIL methods consistently boosts their performance, with F1 score gains up to 10.73\%. All code and data are publicly available at https://github.com/Linfeng-Ye/ASMIL.

Linfeng Ye, Shayan Mohajer Hamidi, Zhixiang Chi, Guang Li, Mert Pilanci, Takahiro Ogawa, Miki Haseyama, Konstantinos N. Plataniotis• 2026

Related benchmarks

TaskDatasetResultRank
Survival PredictionTCGA-LUAD
C-index0.6001
154
Survival PredictionTCGA-UCEC
C-index0.7243
142
Survival PredictionTCGA-BRCA
C-index0.6396
101
Survival PredictionTCGA-BLCA
C-index0.6133
94
Survival AnalysisTCGA-GBMLGG
C-index0.8036
44
Multiple Instance Learning ClassificationMUSK1
Accuracy97.1
26
Multiple Instance Learning ClassificationMUSK2
Accuracy96.8
26
Multiple Instance Learning ClassificationElephant
Accuracy98.5
26
WSI subtypingCAMELYON-16
F1 Score96.5
24
WSI subtypingCAMELYON 17
F1 Score68.9
24
Showing 10 of 17 rows

Other info

Follow for update