# Hard Negative Sample Mining for Whole Slide Image Classification

arXiv: https://arxiv.org/abs/2410.02212 · HTML: https://mlsanity.com/paper/2410.02212/

## 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 (most cited first, 19 of 19)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary](https://mlsanity.com/paper/2006.13932/) (2020)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification](https://mlsanity.com/paper/2307.15254/) (2023)
- [Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification](https://mlsanity.com/paper/2210.03664/) (2022)
- [Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning](https://mlsanity.com/paper/2210.09452/) (2022)
- [Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need](https://mlsanity.com/paper/2307.02249/) (2023)
- [Deep Instance-Level Hard Negative Mining Model for Histopathology Images](https://mlsanity.com/paper/1906.09681/) (2019)
- [Multi-Scale Prototypical Transformer for Whole Slide Image Classification](https://mlsanity.com/paper/2307.02308/) (2023)
- [Deep learning-based assessment of tumor-associated stroma for diagnosing breast cancer in histopathology images](https://mlsanity.com/paper/1702.05803/) (2017)
- [Precise Location Matching Improves Dense Contrastive Learning in Digital Pathology](https://mlsanity.com/paper/2212.12105/) (2022)
- [Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning](https://mlsanity.com/paper/2309.06439/) (2023)

## Built on by (most cited first, 4 of 4)

- [Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning](https://mlsanity.com/paper/2412.01672/) (2024)
- [Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning](https://mlsanity.com/paper/2603.00667/) (2026)
- [LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillation](https://mlsanity.com/paper/2502.02707/) (2025)
- [FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation](https://mlsanity.com/paper/2609.00704/) (2026)

## 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