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

• URL: http://arxiv.org/abs/2603.06658v1
• Date: Sun, 01 Mar 2026 18:31:13 GMT
• Title: ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging
• Abstract summary: We show that attention-based multiple instance learning methods exhibit a new failure mode: unstable attention dynamics.<n>We introduce attention-stabilized multiple instance learning (ASMIL), a novel unified framework.<n>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.
• Score: 95.36377714370325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• vAttention: Verified Sparse Attention [100.98210818821688]
  vAttention is a practical sparse attention mechanism with user-specified $(epsilon, delta)$ guarantees on approximation accuracy (thus, verified)<n>We show that vAttention significantly improves the quality of sparse attention across datasets.<n>It can be deployed in reasoning scenarios to achieve fast decoding without compromising model quality.
  arXiv  Detail & Related papers  (2025-10-07T08:46:08Z)
• AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification [51.525891360380285]
  AHDMIL is an Asymmetric Hierarchical Distillation Multi-Instance Learning framework.<n>It eliminates irrelevant patches through a two-step training process.<n>It consistently outperforms previous state-of-the-art methods in both classification performance and inference speed.
  arXiv  Detail & Related papers  (2025-08-07T07:47:16Z)
• Reducing Variability of Multiple Instance Learning Methods for Digital Pathology [2.9284034606635267]
  Digital pathology has revolutionized the field by enabling the digitization of tissue samples into whole slide images (WSIs)<n>WSIs are often divided into smaller patches with a global label.<n>MIL methods have emerged as a suitable solution for WSI classification.
  arXiv  Detail & Related papers  (2025-06-30T22:10:24Z)
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free [81.65559031466452]
  We conduct experiments to investigate gating-augmented softmax attention variants.<n>We find that a simple modification-applying a head-specific sigmoid gate after the Scaled Dot-Product Attention (SDPA)-consistently improves performance.
  arXiv  Detail & Related papers  (2025-05-10T17:15:49Z)
• Position: From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification [51.95824566163554]
  We argue that well-trained max-pooling-based MIL models can make predictions based on causal factors and avoid relying on spurious correlations.<n>We propose a simple yet effective max-pooling-based MIL method (FocusMIL) that outperforms existing mainstream attention-based methods on two datasets.
  arXiv  Detail & Related papers  (2024-08-18T12:15:22Z)
• Towards Efficient Information Fusion: Concentric Dual Fusion Attention Based Multiple Instance Learning for Whole Slide Images [2.428210413498989]
  We introduce the Concentric Dual Fusion Attention-MIL (CDFA-MIL) framework. CDFA-MIL combines point-to-area feature-colum attention and point-to-point concentric-row attention using concentric patch. Its application has demonstrated exceptional performance, significantly surpassing existing MIL methods in accuracy and F1 scores on prominent datasets.
  arXiv  Detail & Related papers  (2024-03-21T12:23:29Z)
• Slot-Mixup with Subsampling: A Simple Regularization for WSI Classification [13.286360560353936]
  Whole slide image (WSI) classification requires repetitive zoom-in and out for pathologists, as only small portions of the slide may be relevant to detecting cancer. Due to the lack of patch-level labels, multiple instance learning (MIL) is a common practice for training a WSI classifier. One of the challenges in MIL for WSIs is the weak supervision coming only from the slide-level labels, often resulting in severe overfitting. Our approach augments the training dataset by sampling a subset of patches in the WSI without significantly altering the underlying semantics of the original slides.
  arXiv  Detail & Related papers  (2023-11-29T09:18:39Z)
• Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification [12.424186320807888]
  We present Attention-Challenging MIL (ACMIL) to mitigate overfitting. ACMIL combines two techniques based on separate analyses for attention value concentration. This paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge.
  arXiv  Detail & Related papers  (2023-11-13T07:34:53Z)
• Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification [18.679580844360615]
  We propose a new Pseudo-bag Mixup (PseMix) data augmentation scheme to improve the training of MIL models. Our scheme generalizes the Mixup strategy for general images to special WSIs via pseudo-bags. It is designed as an efficient and decoupled method, neither involving time-consuming operations nor relying on MIL model predictions.
  arXiv  Detail & Related papers  (2023-06-28T13:02:30Z)
• ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering [59.77141155608009]
  We propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model. ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our framework in different scenarios, thereby improving its generalization ability; 2) it automatically learns a proper weight for each view, thereby reducing the influence of noises; and 3) it aligns the same instances in different views, thereby decreasing the impact of missing instances.
  arXiv  Detail & Related papers  (2020-11-20T10:37:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.