# Giga-SSL: Self-Supervised Learning for Gigapixel Images

arXiv: https://arxiv.org/abs/2212.03273 · HTML: https://mlsanity.com/paper/2212.03273/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Self supervised contrastive learning for digital histopathology](https://mlsanity.com/paper/2011.13971/) (2020)
- [Intriguing Properties of Contrastive Losses](https://mlsanity.com/paper/2011.02803/) (2020)
- [Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology](https://mlsanity.com/paper/2012.03583/) (2020)
- [Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancers](https://mlsanity.com/paper/2109.05819/) (2021)
- [SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2105.02726/) (2021)
- [A Generalization of the Noisy-Or Model](https://mlsanity.com/paper/1303.1479/) (2013)
- [Multimodal brain tumor classification](https://mlsanity.com/paper/2009.01592/) (2020)
- [Kernel Self-Attention in Deep Multiple Instance Learning](https://mlsanity.com/paper/2005.12991/) (2020)
- [Dual-stream Maximum Self-attention Multi-instance Learning](https://mlsanity.com/paper/2006.05538/) (2020)

## Built on by (most cited first, 24 of 24)

- [Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11643/) (2024)
- [Transcriptomics-guided Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11618/) (2024)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Multistain Pretraining for Slide Representation Learning in Pathology](https://mlsanity.com/paper/2408.02859/) (2024)
- [Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning](https://mlsanity.com/paper/2411.13623/) (2024)
- [GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology](https://mlsanity.com/paper/2504.01009/) (2025)
- [A self-supervised framework for learning whole slide representations](https://mlsanity.com/paper/2402.06188/) (2024)
- [M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image Analysis](https://mlsanity.com/paper/2407.17267/) (2024)
- [Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study](https://mlsanity.com/paper/2505.01109/) (2025)
- [Histopathological Image Classification with Cell Morphology Aware Deep Neural Networks](https://mlsanity.com/paper/2407.08625/) (2024)
- [Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis](https://mlsanity.com/paper/2510.27237/) (2025)
- [PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization](https://mlsanity.com/paper/2503.06482/) (2025)
- [Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review](https://mlsanity.com/paper/2410.19820/) (2024)
- [Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction](https://mlsanity.com/paper/2508.01641/) (2025)
- [Mixed Magnification Aggregation for Generalizable Region-Level Representations in Computational Pathology](https://mlsanity.com/paper/2602.22176/) (2026)
- [A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images](https://mlsanity.com/paper/2603.15967/) (2026)
- [Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Image](https://mlsanity.com/paper/2411.11262/) (2024)
- [Open-source framework for detecting bias and overfitting for large pathology images](https://mlsanity.com/paper/2503.01827/) (2025)
- [Any-to-Any Learning in Computational Pathology via Triplet Multimodal Pretraining](https://mlsanity.com/paper/2505.12711/) (2025)
- [Reducing Variability of Multiple Instance Learning Methods for Digital Pathology](https://mlsanity.com/paper/2507.00292/) (2025)
- [Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning](https://mlsanity.com/paper/2512.03577/) (2025)
- [Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis](https://mlsanity.com/paper/2603.15774/) (2026)
- [LEMON: a foundation model for nuclear morphology in Computational Pathology](https://mlsanity.com/paper/2603.25802/) (2026)

## Abstract (arXiv)

Whole slide images (WSI) are microscopy images of stained tissue slides routinely prepared for diagnosis and treatment selection in medical practice. WSI are very large (gigapixel size) and complex (made of up to millions of cells). The current state-of-the-art (SoTA) approach to classify WSI subdivides them into tiles, encodes them by pre-trained networks and applies Multiple Instance Learning (MIL) to train for specific downstream tasks. However, annotated datasets are often small, typically a few hundred to a few thousand WSI, which may cause overfitting and underperforming models. Conversely, the number of unannotated WSI is ever increasing, with datasets of tens of thousands (soon to be millions) of images available. While it has been previously proposed to use these unannotated data to identify suitable tile representations by self-supervised learning (SSL), downstream classification tasks still require full supervision because parts of the MIL architecture is not trained during tile level SSL pre-training. Here, we propose a strategy of slide level SSL to leverage the large number of WSI without annotations to infer powerful slide representations. Applying our method to The Cancer-Genome Atlas, one of the most widely used data resources in cancer research (16 TB image data), we are able to downsize the dataset to 23 MB without any loss in predictive power: we show that a linear classifier trained on top of these embeddings maintains or improves previous SoTA performances on various benchmark WSI classification tasks. Finally, we observe that training a classifier on these representations with tiny datasets (e.g. 50 slides) improved performances over SoTA by an average of +6.3 AUC points over all downstream tasks.