# Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

arXiv: https://arxiv.org/abs/2411.13623 · HTML: https://mlsanity.com/paper/2411.13623/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 20 Nov 2024.

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

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [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)
- [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)
- [Video Representation Learning by Dense Predictive Coding](https://mlsanity.com/paper/1909.04656/) (2019)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations](https://mlsanity.com/paper/2008.05571/) (2020)
- [PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology](https://mlsanity.com/paper/2405.10254/) (2024)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Transcriptomics-guided Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11618/) (2024)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [Multistain Pretraining for Slide Representation Learning in Pathology](https://mlsanity.com/paper/2408.02859/) (2024)
- [Giga-SSL: Self-Supervised Learning for Gigapixel Images](https://mlsanity.com/paper/2212.03273/) (2022)
- [Regression-based Deep-Learning predicts molecular biomarkers from pathology slides](https://mlsanity.com/paper/2304.05153/) (2023)
- [Benchmarking Pathology Feature Extractors for Whole Slide Image Classification](https://mlsanity.com/paper/2311.11772/) (2023)
- [SLPD: Slide-level Prototypical Distillation for WSIs](https://mlsanity.com/paper/2307.10696/) (2023)

## Built on by (most cited first, 15 of 15)

- [Atlas: A Novel Pathology Foundation Model by Mayo Clinic, Charit'e, and Aignostics](https://mlsanity.com/paper/2501.05409/) (2025)
- [Foundation Models in Medical Imaging: A Review and Outlook](https://mlsanity.com/paper/2506.09095/) (2025)
- [PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialogue](https://mlsanity.com/paper/2506.13063/) (2025)
- [Atlas 2 -- Foundation models for clinical deployment](https://mlsanity.com/paper/2601.05148/) (2026)
- [TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning](https://mlsanity.com/paper/2512.21331/) (2025)
- [Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis](https://mlsanity.com/paper/2510.27237/) (2025)
- [Ensemble learning of pathology foundation models for precision oncology](https://mlsanity.com/paper/2508.16085/) (2025)
- [Whole Slide Concepts: A Supervised Foundation Model For Pathological Images](https://mlsanity.com/paper/2507.05742/) (2025)
- [MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expression](https://mlsanity.com/paper/2510.11344/) (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)
- [AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models](https://mlsanity.com/paper/2508.05084/) (2025)
- [Higher-Order Certified Robustness for Regression](https://mlsanity.com/paper/2607.05536/) (2026)
- [Understanding Synergistic Interactions among Pathology Foundation Models via Adaptive Fusion](https://mlsanity.com/paper/2608.01370/) (2026)
- [Synergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2609.02118/) (2026)

## Abstract (arXiv)

Representation learning of pathology whole-slide images (WSIs) has primarily relied on weak supervision with Multiple Instance Learning (MIL). This approach leads to slide representations highly tailored to a specific clinical task. Self-supervised learning (SSL) has been successfully applied to train histopathology foundation models (FMs) for patch embedding generation. However, generating patient or slide level embeddings remains challenging. Existing approaches for slide representation learning extend the principles of SSL from patch level learning to entire slides by aligning different augmentations of the slide or by utilizing multimodal data. By integrating tile embeddings from multiple FMs, we propose a new single modality SSL method in feature space that generates useful slide representations. Our contrastive pretraining strategy, called COBRA, employs multiple FMs and an architecture based on Mamba-2. COBRA exceeds performance of state-of-the-art slide encoders on four different public Clinical Protemic Tumor Analysis Consortium (CPTAC) cohorts on average by at least +4.4% AUC, despite only being pretrained on 3048 WSIs from The Cancer Genome Atlas (TCGA). Additionally, COBRA is readily compatible at inference time with previously unseen feature extractors. Code available at https://github.com/KatherLab/COBRA.