ScholarMate
English简体中文繁體中文
Customer service: 400-1616-289
Sign inSign up
Conference paper

Rethinking Overfitting of Multiple Instance Learning for Whole Slide Image Classification

Song, Hongjian; Tang, Jie; Xiao, Hongzhao; Hu, Juncheng*
IEEE International Conference on Multimedia and Expo (ICME)2023DOI: 10.1109/ICME55011.2023.00100
6Reads
CiteSave
Share

Abstract

Multiple instance learning(MIL) is widely used for whole slide image(WSI) classification. However, these methods suffer from severe overfitting. In this paper, we introduce two main causes of such overfitting problems by rethinking the MIL task and formulation of attention-based MIL models: (i) The model is sensitive to the proportion of positive regions, and (ii)incorrectly learns the positional relationship of patches (i.e., the order of instances). To this end, we propose recurrent random padding(RRP) module and patch shuffle(PS) module to tackle these two issues, respectively. Furthermore, we present random alignment(RA) algorithm to solve these two overfitting problems simultaneously. On CAMELYON16 and TCGA-NSCLC, the proposed plug-and-play modules improve the performance of six baselines by large margins. The significant and consistent refinement demonstrates the correctness of our theories and the effectiveness of our modules.

Disciplines and keywords

Keywords
Multiple instance learningwhole slide image classificationoverfitrandom alignmentrecurrent random padding
Related
Loading…
  • Bayesian Collaborative Learning for Whole-Slide Image Classification
    Yu, Jin-Gang; Wu, Zihao; Ming, Yu; Deng, Shule; Wu, Qihang; Xiong, Zhongtang; Yu, Tianyou; Xia, Gui-Song; Jiang, Qingping*; Li, Yuanqing*IEEE Transactions on Medical Imaging, 2023, 42(6): 1809-1821.
  • Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification
    Tang, Kunming; Jiang, Zhiguo; Wu, Kun; Shi, Jun; Xie, Fengying; Wang, Wei; Wu, Haibo*; Zheng, Yushan*IEEE Transactions on Medical Imaging, 2025, 44(1): 462-474.
  • Unsupervised mutual transformer learning for multi-gigapixel Whole Slide Image classification
    Javed, Sajid*; Mahmood, Arif; Qaiser, Talha; Werghi, Naoufel; Rajpoot, NasirMedical Image Analysis, 2024, 96: 103203.
View all →

Conference information

Conference name
IEEE International Conference on Multimedia and Expo (ICME)
Conference dates
2023-07-10 to 2023-07-14
Proceedings title
2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME
Publication date
2023
Page range
546-551
DOI
10.1109/ICME55011.2023.00100
Funding acknowledgment
South China University of Technology -Guilin Medical University 5G Intelligent Medical Platform and Demonstration Base Construction [AD21075054]; Special Program of Base Construction and Outstanding Scholarship for Science and Technology Department of Guangxi Province
Indexed in
ISTP

Authors

  • S

    Song, Hongjian (First author)

  • T

    Tang, Jie

View all 4 authorsShow fewer authors
  • X

    Xiao, Hongzhao

  • H

    Hu, Juncheng (Corresponding)

Sign in for more features

  • Save this paper in My collections
  • Claim your outputs and generate promotion materials
  • Follow authors for new outputs
  • Join groups and collaborate
Sign up / Sign in

Products

  • ScholarMate
  • InnoCity
  • IRISaaS

Support

  • Help Center
  • Privacy Policy
  • Terms of Service

Contact

Online support: []
Customer service: 400-1616-289
Email: support@scholarmate.com

Follow or download ScholarMate

WeChat QR code
WeChat official account
App download QR code
Download the app
OutputsResearchersResearch institutionsResearch newsIRISaaS

©2026 深圳市科研之友网络服务有限公司

Public security registration badge粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417