mlsanityData to 7 Oct 2026

AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Image

arXiv 2602.20187 ↗First posted 21 Feb 2026eess.IV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in multi-instance learning (MIL) have witnessed impressive performance in whole slide image (WSI) analysis. However, the inherent sparsity of tumors and their morphological diversity lead to obvious heterogeneity across regions, posing significant challenges in aggregating high-quality and discriminative representations. To address this, we introduce a novel concept of anchor instance (AI), a compact subset of instances that are representative within their regions (local) and discriminative at the bag (global) level. These AIs act as semantic references to guide interactions across regions, correcting non-discriminative patterns while preserving regional diversity. Specifically, we propose a dual-level anchor mining (DAM) module to select AIs from massive instances, where the most informative AI in each region is extracted by assessing its similarity to both local and global embeddings. Furthermore, to ensure completeness and diversity, we devise an anchor-guided region correction (ARC) module that explores the complementary information from all regions to correct each regional representation. Building upon DAM and ARC, we develop a concise yet effective framework, AINet, which employs a simple predictor and surpasses state-of-the-art methods with substantially fewer FLOPs and parameters. Moreover, both DAM and ARC are modular and can be seamlessly integrated into existing MIL frameworks, consistently improving their performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 21 Feb 2026.

Builds on

36 of 55 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  3. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  4. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  5. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  6. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  7. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  8. 2015Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classificationcited by 159
  9. 2021BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Imagescited by 130
  10. 2018Anchor regression: heterogeneous data meets causalitycited by 116
  11. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  12. 2024MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathologycited by 87
24 more
  1. 2020Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Imagescited by 81
  2. 2024Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathologycited by 70
  3. 2024Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathologycited by 66
  4. 2024Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysiscited by 66
  5. 2023Attention-Challenging Multiple Instance Learning for Whole Slide Image Classificationcited by 61
  6. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 58
  7. 2023Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classificationcited by 54
  8. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  9. 2023Structured State Space Models for Multiple Instance Learning in Digital Pathologycited by 41
  10. 20242DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classificationcited by 35
  11. 2024CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathologycited by 34
  12. 2025ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classificationcited by 28
  13. 2024Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interactioncited by 27
  14. 2024Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Predictioncited by 20
  15. 2024FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classificationcited by 20
  16. 2023Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classificationcited by 18
  17. 2024MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Imagescited by 17
  18. 2023Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classificationcited by 12
  19. 2024Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classificationcited by 12
  20. 2022Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learnerscited by 11
  21. 2023Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learningcited by 7
  22. 2023ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classificationcited by 5
  23. 2024Discriminative Anchor Learning for Efficient Multi-view Clusteringcited by 1
  24. 2025Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imagingcited by 1

Built on by

Not cited yet.