mlsanityData to 7 Oct 2026

Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology

arXiv 2408.00738 ↗First posted 1 Aug 2024cs.CVcited by 144

Not on the map. Why?

Abstract (arXiv)

Foundation models are rapidly being developed for computational pathology applications. However, it remains an open question which factors are most important for downstream performance with data scale and diversity, model size, and training algorithm all playing a role. In this work, we propose algorithmic modifications, tailored for pathology, and we present the result of scaling both data and model size, surpassing previous studies in both dimensions. We introduce three new models: Virchow2, a 632 million parameter vision transformer, Virchow2G, a 1.9 billion parameter vision transformer, and Virchow2G Mini, a 22 million parameter distillation of Virchow2G, each trained with 3.1 million histopathology whole slide images, with diverse tissues, originating institutions, and stains. We achieve state of the art performance on 12 tile-level tasks, as compared to the top performing competing models. Our results suggest that data diversity and domain-specific methods can outperform models that only scale in the number of parameters, but, on average, performance benefits from the combination of domain-specific methods, data scale, and model scale.

Key facts. Cited by 144 papers in the map (data through 7 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

46 of 64 references.

References · 46

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2020Scaling Laws for Neural Language Modelscited by 6,411
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
34 more
  1. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  2. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  4. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  5. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  6. 2021Scaling Vision Transformerscited by 993
  7. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  8. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  9. 2023Vision Transformers Need Registerscited by 844
  10. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  11. 2018Rotation Equivariant CNNs for Digital Pathologycited by 420
  12. 2023A Cookbook of Self-Supervised Learningcited by 248
  13. 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 172
  14. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 148
  15. 2020Self supervised contrastive learning for digital histopathologycited by 146
  16. 2021Decoupled Contrastive Learningcited by 141
  17. 2018Spreading vectors for similarity searchcited by 114
  18. 2024HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysiscited by 104
  19. 2021Towards the Generalization of Contrastive Self-Supervised Learningcited by 99
  20. 2023Stable and low-precision training for large-scale vision-language modelscited by 74
  21. 2022The Effects of Regularization and Data Augmentation are Class Dependentcited by 67
  22. 2021A Petri Dish for Histopathology Image Analysiscited by 63
  23. 2023A Theory on Adam Instability in Large-Scale Machine Learningcited by 54
  24. 2024Hibou: A Family of Foundational Vision Transformers for Pathologycited by 52
  25. 2024RudolfV: A Foundation Model by Pathologists for Pathologistscited by 40
  26. 2022RandStainNA: Learning Stain-Agnostic Features from Histology Slides by Bridging Stain Augmentation and Normalizationcited by 32
  27. 2023Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Imagescited by 30
  28. 2023Towards Democratizing Joint-Embedding Self-Supervised Learningcited by 18
  29. 2024PLUTO: Pathology-Universal Transformercited by 17
  30. 2024You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learningcited by 16
  31. 2023Dual PatchNormcited by 9
  32. 2020DLBCL-Morph: Morphological features computed using deep learning for an annotated digital DLBCL image setcited by 8
  33. 2023Synthetic DOmain-Targeted Augmentation (S-DOTA) Improves Model Generalization in Digital Pathologycited by 6
  34. 2022Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlapscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 66; 2026: 67.

144 papers.

Sort:

By area:

  1. 2024Multimodal Whole Slide Foundation Model for Pathologycited by 156
  2. 2025LLM Agents Making Agent Toolscited by 45
  3. 2025Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Imagescited by 35
  4. 2025Distilling foundation models for robust and efficient models in digital pathologycited by 33
  5. 2025Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learningcited by 33
  6. 2025CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logiccited by 27
  7. 2024Specialized Foundation Models Struggle to Beat Supervised Baselinescited by 23
  8. 2024Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosiscited by 21
  9. 2025Training state-of-the-art pathology foundation models with orders of magnitude less datacited by 19
  10. 2025PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncologycited by 19
  11. 2025A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Taskscited by 15
  12. 2025A Survey of Pathology Foundation Model: Progress and Future Directionscited by 14
38 more
  1. 2025PixCell: A generative foundation model for digital histopathology imagescited by 11
  2. 2024A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Modelscited by 9
  3. 2025Multi-Modal Foundation Models for Computational Pathology: A Surveycited by 9
  4. 2026Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Modelscited by 9
  5. 2024Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shiftscited by 8
  6. 2025SurGen: 1020 H&E-stained Whole Slide Images With Survival and Genetic Markerscited by 8
  7. 2025PRISM2: Unlocking Multi-Modal General Pathology AI with Clinical Dialoguecited by 8
  8. 2025Foundation Models in Medical Imaging: A Review and Outlookcited by 7
  9. 2025Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluationcited by 7
  10. 2025Pathology Foundation Models are Scanner Sensitive: Benchmark and Mitigation with Contrastive ScanGen Losscited by 7
  11. 2025Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challengescited by 5
  12. 2025Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysiscited by 5
  13. 2024RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistencycited by 4
  14. 2024Gen-SIS: Generative Self-augmentation Improves Self-supervised Learningcited by 4
  15. 2025Ensemble learning of pathology foundation models for precision oncologycited by 4
  16. 2025Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddingscited by 4
  17. 2025Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtypingcited by 3
  18. 2025SPADE: Spatial Transcriptomics and Pathology Alignment Using a Mixture of Data Experts for an Expressive Latent Spacecited by 3
  19. 2025Streamline pathology foundation model by cross-magnification distillationcited by 3
  20. 2025Beyond Pixel Simulation: Pathology Image Generation via Diagnostic Semantic Tokens and Prototype Controlcited by 3
  21. 2025PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosiscited by 3
  22. 2026MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understandingcited by 3
  23. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 2
  24. 2025Benchmarking Foundation Models for Mitotic Figure Classificationcited by 2
  25. 2025Controllable Latent Space Augmentation for Digital Pathologycited by 2
  26. 2025G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillationcited by 2
  27. 2025Universal and Transferable Attacks on Pathology Foundation Modelscited by 2
  28. 2025PLUTO-4: Frontier Pathology Foundation Modelscited by 2
  29. 2025Supervise Less, See More: Training-free Nuclear Instance Segmentation with Prototype-Guided Promptingcited by 2
  30. 2026Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathologycited by 2
  31. 2026OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGAcited by 2
  32. 2024INSIGHT: Explainable Weakly-Supervised Medical Image Analysiscited by 1
  33. 2025A Lightweight and Extensible Cell Segmentation and Classification Model for Whole Slide Imagescited by 1
  34. 2025Unifying Multiple Foundation Models for Advanced Computational Pathologycited by 1
  35. 2025PhenoBench: A Comprehensive Benchmark for Cell Phenotypingcited by 1
  36. 2025MVHybrid: Improving Spatial Transcriptomics Prediction with Hybrid State Space-Vision Transformer Backbone in Pathology Vision Foundation Modelscited by 1
  37. 2025MMAP: A Multi-Magnification and Prototype-Aware Architecture for Predicting Spatial Gene Expressioncited by 1
  38. 2025Towards Cellular-Scale Interpretability in Pathology Foundation Models for Biomarker Assessmentcited by 1

50 most cited of 144 All 144 (JSON)