mlsanityData to 7 Oct 2026

Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

arXiv 2402.17228 ↗First posted 27 Feb 2024cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks, limiting its adaptability and performance. To address this issue, we propose a Re-embedded Regional Transformer (R2T) for re-embedding the instance features online, which captures fine-grained local features and establishes connections across different regions. Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R2T is tailored to re-embed instance features online. It serves as a portable module that can seamlessly integrate into mainstream MIL models. Extensive experimental results on common computational pathology tasks validate that: 1) feature re-embedding improves the performance of MIL models based on ResNet-50 features to the level of foundation model features, and further enhances the performance of foundation model features; 2) the R2T can introduce more significant performance improvements to various MIL models; 3) R2T-MIL, as an R2T-enhanced AB-MIL, outperforms other latest methods by a large margin.The code is available at: https://github.com/DearCaat/RRT-MIL.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 28 of its 53 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

28 of 53 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  7. 2018Self-Attention with Relative Position Representationscited by 1,112
  8. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  9. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  10. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  11. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  12. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 468
16 more
  1. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  2. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  3. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  4. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  5. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  6. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  7. 2020Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networkscited by 178
  8. 2021GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graphcited by 143
  9. 2023Artificial Intelligence for Digital and Computational Pathologycited by 106
  10. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  11. 2019CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentationcited by 73
  12. 2023Cross-Modal Translation and Alignment for Survival Analysiscited by 70
  13. 2021Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classificationcited by 65
  14. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  15. 2019Deep learning-based survival prediction for multiple cancer types using histopathology imagescited by 47
  16. 2021Self supervised learning improves dMMR/MSI detection from histology slides across multiple cancerscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 32; 2026: 21.

66 papers.

Sort:

By area:

  1. 2025Do Multiple Instance Learning Models Transfer?cited by 28
  2. 2024Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Predictioncited by 20
  3. 2024MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuningcited by 16
  4. 2024Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysiscited by 11
  5. 2024Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancementcited by 11
  6. 2024A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Modelscited by 9
  7. 2024FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classificationcited by 8
  8. 2024SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Predictioncited by 7
  9. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  10. 2024MergeUp-augmented Semi-Weakly Supervised Learning for WSI Classificationcited by 7
  11. 2025MiCo: Multiple Instance Learning with Context-Aware Clustering for Whole Slide Image Analysiscited by 7
  12. 2025Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representationcited by 6
38 more
  1. 2026CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysiscited by 6
  2. 2026Multimodal Model for Computational Pathology:Representation Learning and Image Compressioncited by 6
  3. 2025Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysiscited by 5
  4. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 5
  5. 2024RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistencycited by 4
  6. 2025MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classificationcited by 3
  7. 2025Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?cited by 3
  8. 2025PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Predictioncited by 3
  9. 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learningcited by 3
  10. 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantizationcited by 2
  11. 2025Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysiscited by 2
  12. 2025HiLa: Hierarchical Vision-Language Collaboration for Cancer Survival Predictioncited by 2
  13. 2025Multi-modal Knowledge Decomposition based Online Distillation for Biomarker Prediction in Breast Cancer Histopathologycited by 2
  14. 2026Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathologycited by 2
  15. 2026Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Stainingcited by 2
  16. 2026PathSelect: Sequential Token Selection for Whole Slide Pathologycited by 2
  17. 2024Learning Spatial-Preserving Hierarchical Representations for Digital Pathologycited by 1
  18. 2024Unlocking adaptive digital pathology through dynamic feature learningcited by 1
  19. 2025Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classificationcited by 1
  20. 2025Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstructioncited by 1
  21. 2025Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysiscited by 1
  22. 2025Morphology-Aware Prognostic model for Five-Year Survival Prediction in Colorectal Cancer from H&E Whole Slide Imagescited by 1
  23. 2025MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Imagecited by 1
  24. 2026AtlasPatch: Scalable Foundation Model-based Tissue Detection and Patch Extraction for Computational Pathologycited by 1
  25. 2026Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoningcited by 1
  26. 2024Mitigating Downstream Model Risks via Model Provenancecited by 0
  27. 2025LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-Distillationcited by 0
  28. 2025VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstructioncited by 0
  29. 2025Cross-Modal Prototype Allocation: Unsupervised Slide Representation Learning via Patch-Text Contrast in Computational Pathologycited by 0
  30. 2025SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Imagescited by 0
  31. 2025Dual-stream attention-guided learning for weakly supervised whole slide image classificationcited by 0
  32. 2025Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Imagescited by 0
  33. 2025Classification of autoimmune diseases from Peripheral blood TCR repertoires by multimodal multi-instance learningcited by 0
  34. 2025Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classificationcited by 0
  35. 2025SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 0
  36. 2025C2MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysiscited by 0
  37. 2025Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Frameworkcited by 0
  38. 2025Fourier Transform Multiple Instance Learning for Whole Slide Image Classificationcited by 0

50 most cited of 66 All 66 (JSON)