mlsanityData to 7 Oct 2026

Snuffy: Efficient Whole Slide Image Classifier

arXiv 2408.08258 ↗First posted 15 Aug 2024cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Whole Slide Image (WSI) classification with multiple instance learning (MIL) in digital pathology faces significant computational challenges. Current methods mostly rely on extensive self-supervised learning (SSL) for satisfactory performance, requiring long training periods and considerable computational resources. At the same time, no pre-training affects performance due to domain shifts from natural images to WSIs. We introduce Snuffy architecture, a novel MIL-pooling method based on sparse transformers that mitigates performance loss with limited pre-training and enables continual few-shot pre-training as a competitive option. Our sparsity pattern is tailored for pathology and is theoretically proven to be a universal approximator with the tightest probabilistic sharp bound on the number of layers for sparse transformers, to date. We demonstrate Snuffy's effectiveness on CAMELYON16 and TCGA Lung cancer datasets, achieving superior WSI and patch-level accuracies. The code is available on https://github.com/jafarinia/snuffy.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 15 Aug 2024.

Builds on

35 of 54 references.

References · 35

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2020Longformer: The Long-Document Transformercited by 3,362
  10. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  12. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
23 more
  1. 2017Deep Setscited by 1,394
  2. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  3. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  4. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  5. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  6. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  7. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 549
  8. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 485
  9. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
  10. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 468
  11. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 443
  12. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  13. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 254
  14. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 178
  15. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 148
  16. 2022Better plain ViT baselines for ImageNet-1kcited by 97
  17. 2019Star-Transformercited by 94
  18. 2020O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformerscited by 82
  19. 2022DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classificationcited by 40
  20. 2021Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imagingcited by 31
  21. 2019Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Surveycited by 28
  22. 2023PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessmentcited by 19
  23. 2023PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Imagescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classificationcited by 3
  2. 2025FrameShield: Adversarially Robust Video Anomaly Detectioncited by 2
  3. 2025GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classificationcited by 1
  4. 2025Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learningcited by 0
  5. 2026Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysiscited by 0
  6. 2026Learning Where to Focus: Self-Supervised Multi-Scale ViTs for Histopathologycited by 0