mlsanityData to 14 Oct 2026

Rethinking Attention-Based Multiple Instance Learning for Whole-Slide Pathological Image Classification: An Instance Attribute Viewpoint

arXiv 2404.00351 ↗First posted 30 Mar 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Multiple instance learning (MIL) is a robust paradigm for whole-slide pathological image (WSI) analysis, processing gigapixel-resolution images with slide-level labels. As pioneering efforts, attention-based MIL (ABMIL) and its variants are increasingly becoming popular due to the characteristics of simultaneously handling clinical diagnosis and tumor localization. However, the attention mechanism exhibits limitations in discriminating between instances, which often misclassifies tissues and potentially impairs MIL performance. This paper proposes an Attribute-Driven MIL (AttriMIL) framework to address these issues. Concretely, we dissect the calculation process of ABMIL and present an attribute scoring mechanism that measures the contribution of each instance to bag prediction effectively, quantifying instance attributes. Based on attribute quantification, we develop a spatial attribute constraint and an attribute ranking constraint to model instance correlations within and across slides, respectively. These constraints encourage the network to capture the spatial correlation and semantic similarity of instances, improving the ability of AttriMIL to distinguish tissue types and identify challenging instances. Additionally, AttriMIL employs a histopathology adaptive backbone that maximizes the pre-trained model's feature extraction capability for collecting pathological features. Extensive experiments on three public benchmarks demonstrate that our AttriMIL outperforms existing state-of-the-art frameworks across multiple evaluation metrics. The implementation code is available at https://github.com/MedCAI/AttriMIL.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 30 Mar 2024.

Builds on

25 of 36 references.

References · 25

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  5. 2018Group Normalizationcited by 1,524
  6. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  7. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  8. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  9. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  10. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  11. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  12. 2019Deep neural network models for computational histopathology: A surveycited by 165
13 more
  1. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  2. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 150
  3. 2023AIM: Adapting Image Models for Efficient Video Action Recognitioncited by 148
  4. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  5. 2020Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primarycited by 89
  6. 2022Parameter-efficient Model Adaptation for Vision Transformerscited by 81
  7. 2022Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNetscited by 62
  8. 2023Hard Patches Mining for Masked Image Modelingcited by 57
  9. 2022DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 40
  10. 2021UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia gradingcited by 33
  11. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Needcited by 22
  12. 2022Interventional Multi-Instance Learning with Deconfounded Instance-Level Predictioncited by 13
  13. 2023The Importance of Downstream Networks in Digital Pathology Foundation Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Imagescited by 0
  2. 2026Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathologycited by 0