mlsanityData to 14 Oct 2026

Hard Negative Sample Mining for Whole Slide Image Classification

arXiv 2410.02212 ↗First posted 3 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Weakly supervised whole slide image (WSI) classification is challenging due to the lack of patch-level labels and high computational costs. State-of-the-art methods use self-supervised patch-wise feature representations for multiple instance learning (MIL). Recently, methods have been proposed to fine-tune the feature representation on the downstream task using pseudo labeling, but mostly focusing on selecting high-quality positive patches. In this paper, we propose to mine hard negative samples during fine-tuning. This allows us to obtain better feature representations and reduce the training cost. Furthermore, we propose a novel patch-wise ranking loss in MIL to better exploit these hard negative samples. Experiments on two public datasets demonstrate the efficacy of these proposed ideas. Our codes are available at https://github.com/winston52/HNM-WSI

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

19 of 31 references.

References · 19

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2020Supervised Contrastive Learningcited by 2,829
  4. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  5. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  6. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  7. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 359
  8. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  9. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  10. 2020Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primarycited by 89
  11. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 60
  12. 2022Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classificationcited by 43
7 more
  1. 2022Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learningcited by 22
  2. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Needcited by 22
  3. 2019Deep Instance-Level Hard Negative Mining Model for Histopathology Imagescited by 12
  4. 2023Multi-Scale Prototypical Transformer for Whole Slide Image Classificationcited by 9
  5. 2017Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology imagescited by 8
  6. 2022Precise Location Matching Improves Dense Contrastive Learning in Digital Pathologycited by 4
  7. 2023Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Gen-SIS: Generative Self-augmentation Improves Self-supervised Learningcited by 5
  2. 2026Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoningcited by 5
  3. 2025LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillationcited by 0
  4. 2026FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentationcited by 0