TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Snuffy: Efficient Whole Slide Image Classifier

Snuffy: Efficient Whole Slide Image Classifier

Hossein Jafarinia, Alireza Alipanah, Danial Hamdi, Saeed Razavi, Nahal Mirzaie, Mohammad Hossein Rohban

2024-08-15Breast Cancer DetectionSelf-Supervised LearningMultiple Instance LearningLung Cancer Diagnosis
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Multiple Instance LearningElephantACC0.923Snuffy
Multiple Instance LearningElephantAUC0.967Snuffy
Multiple Instance LearningMusk v1ACC0.961Snuffy
Multiple Instance LearningMusk v1AUC0.989Snuffy
Multiple Instance LearningTCGAACC0.947Snuffy (SimCLR Exhaustive)
Multiple Instance LearningTCGAAUC0.972Snuffy (SimCLR Exhaustive)
Multiple Instance LearningMusk v2ACC0.789Snuffy
Multiple Instance LearningMusk v2AUC0.985Snuffy
Multiple Instance LearningCAMELYON16ACC0.948Snuffy (DINO Exhaustive)
Multiple Instance LearningCAMELYON16AUC0.987Snuffy (DINO Exhaustive)
Multiple Instance LearningCAMELYON16Expected Calibration Error0.083Snuffy (DINO Exhaustive)
Multiple Instance LearningCAMELYON16FROC0.675Snuffy (DINO Exhaustive)
Multiple Instance LearningCAMELYON16Patch AUC0.957Snuffy (DINO Exhaustive)
Multiple Instance LearningCAMELYON16ACC0.952Snuffy (SimCLR Exhaustive)
Multiple Instance LearningCAMELYON16AUC0.97Snuffy (SimCLR Exhaustive)
Multiple Instance LearningCAMELYON16Expected Calibration Error0.057Snuffy (SimCLR Exhaustive)
Multiple Instance LearningCAMELYON16FROC0.622Snuffy (SimCLR Exhaustive)
Multiple Instance LearningCAMELYON16Patch AUC0.98Snuffy (SimCLR Exhaustive)
Multiple Instance LearningCAMELYON16ACC0.9Snuffy (MAE Adapter)
Multiple Instance LearningCAMELYON16AUC0.91Snuffy (MAE Adapter)
Multiple Instance LearningCAMELYON16Expected Calibration Error0.078Snuffy (MAE Adapter)
Multiple Instance LearningCAMELYON16FROC0.543Snuffy (MAE Adapter)
Multiple Instance LearningCAMELYON16Patch AUC0.873Snuffy (MAE Adapter)

Related Papers

A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys2025-07-17Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder2025-07-14GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning2025-07-09Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis2025-07-08World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model2025-07-01ShapeEmbed: a self-supervised learning framework for 2D contour quantification2025-07-01The Trilemma of Truth in Large Language Models2025-06-30RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models2025-06-27