mlsanityData to 7 Oct 2026

GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis

arXiv 2510.03555 ↗First posted 3 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Foundation models (FMs) have transformed computational pathology by providing powerful, general-purpose feature extractors. However, adapting and benchmarking individual FMs for specific diagnostic tasks is often time-consuming and resource-intensive, especially given their scale and diversity. To address this challenge, we introduce Group-Aggregative Selection Multi-Instance Learning (GAS-MIL), a flexible ensemble framework that seamlessly integrates features from multiple FMs, preserving their complementary strengths without requiring manual feature selection or extensive task-specific fine-tuning. Across classification tasks in three cancer datasets-prostate (PANDA), ovarian (UBC-OCEAN), and breast (TCGA-BrCa)-GAS-MIL consistently achieves superior or on-par performance relative to individual FMs and established MIL methods, demonstrating its robustness and generalizability. By enabling efficient integration of heterogeneous FMs, GAS-MIL streamlines model deployment for pathology and provides a scalable foundation for future multimodal and precision oncology applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

20 of 41 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023Segment Anythingcited by 8,158
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  10. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  11. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  12. 2023LongNet: Scaling Transformers to 1,000,000,000 Tokenscited by 201
8 more
  1. 2024Phikon-v2, A large and public feature extractor for biomarker predictioncited by 67
  2. 2023LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matchingcited by 60
  3. 2020A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysiscited by 45
  4. 2018Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approachcited by 33
  5. 2020Interpretable Survival Prediction for Colorectal Cancer using Deep Learningcited by 30
  6. 2024Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarioscited by 16
  7. 2019Multimodal Multitask Representation Learning for Pathology Biobank Metadata Predictioncited by 10
  8. 2024Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directionscited by 7

Built on by

Not cited yet.