Papers › Snuffy: Efficient Whole Slide Image Classifier

Snuffy: Efficient Whole Slide Image Classifier

15 Aug 2024arXiv:2408.08258archive 2025-07-28

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

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jafarinia/snuffy officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Breast Cancer DetectionLung Cancer DiagnosisMultiple Instance LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multiple Instance Learning CAMELYON16 Snuffy (DINO Exhaustive) ACC 0.948 #1 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (DINO Exhaustive) AUC 0.987 #1 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (DINO Exhaustive) Expected Calibration Error 0.083 #1 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (DINO Exhaustive) FROC 0.675 #1 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (DINO Exhaustive) Patch AUC 0.957 #1 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (SimCLR Exhaustive) ACC 0.952 #2 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (SimCLR Exhaustive) AUC 0.970 #2 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (SimCLR Exhaustive) Expected Calibration Error 0.057 #2 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (SimCLR Exhaustive) FROC 0.622 #2 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (SimCLR Exhaustive) Patch AUC 0.980 #2 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (MAE Adapter) ACC 0.900 #11 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (MAE Adapter) AUC 0.910 #11 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (MAE Adapter) Expected Calibration Error 0.078 #11 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (MAE Adapter) FROC 0.543 #11 of 14 Archive leaderboard report
Multiple Instance Learning CAMELYON16 Snuffy (MAE Adapter) Patch AUC 0.873 #11 of 14 Archive leaderboard report
Multiple Instance Learning Elephant Snuffy ACC 0.923 #1 of 2 Archive leaderboard report
Multiple Instance Learning Elephant Snuffy AUC 0.967 #1 of 2 Archive leaderboard report
Multiple Instance Learning Musk v1 Snuffy ACC 0.961 #1 of 2 Archive leaderboard report
Multiple Instance Learning Musk v1 Snuffy AUC 0.989 #1 of 2 Archive leaderboard report
Multiple Instance Learning Musk v2 Snuffy ACC 0.789 #2 of 2 Archive leaderboard report
Multiple Instance Learning Musk v2 Snuffy AUC 0.985 #2 of 2 Archive leaderboard report
Multiple Instance Learning TCGA Snuffy (SimCLR Exhaustive) ACC 0.947 #2 of 8 Archive leaderboard report
Multiple Instance Learning TCGA Snuffy (SimCLR Exhaustive) AUC 0.972 #2 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections