Datasets › PCam
PCam (PatchCamelyon)
PatchCamelyon is an image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annotated with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than ImageNet, trainable on a single GPU.
Benchmarks archive 2025-07-28
All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Breast Tumour Classification | PCam | DSF-CNN (C8) AUC 0.975 | Dense Steerable Filter CNNs for Exploiting Rotational... | simongraham/dsf-cnn +1 | 16 | Compare |
| Image Clustering | PCam | TURTLE (CLIP + DINOv2) Accuracy 52.0 | Let Go of Your Labels with Unsupervised Transfer | mlbio-epfl/turtle | 1 | Compare |
| Image Compression | PCam | Lossyless Compressor Bit rate 1490 | Lossy Compression for Lossless Prediction | YannDubs/lossyless | 1 | Compare |
| Image Classification | PCam | no rows | — | — | 0 | Compare |
Papers archive 2025-07-28
11 shown of 11 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 110. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Let Go of Your Labels with Unsupervised Transfer | 1 | 1 | 11 Jun 2024 | ran 3 of 4 samples (1 unverified; 4 pointer-only for licence) |
| Virchow: A Million-Slide Digital Pathology Foundation Model | 1 | 1 | 14 Sep 2023 | ran 9 of 9 samples (0 unverified; 9 pointer-only for licence) |
| Lossy Compression for Lossless Prediction | 1 | 1 | 21 Jun 2021 | ran 2 of 11 samples (9 unverified) |
| Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images | 2 | 1 | 6 Apr 2020 | ran 1 of 1 samples (0 unverified) |
| Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis | 1 | 2 | 20 Feb 2020 | ran 0 of 6 samples (6 unverified) |
| Rotation Equivariant CNNs for Digital Pathology | 4 | 1 | 8 Jun 2018 | not harvested |
| Learning Steerable Filters for Rotation Equivariant CNNs | 0 | 4 | 20 Nov 2017 | not harvested |
| Rotation equivariant vector field networks | 3 | 3 | 29 Dec 2016 | not harvested |
| Densely Connected Convolutional Networks | 146 | 1 | 25 Aug 2016 | ran 18 of 71 samples (53 unverified; 7 pointer-only for licence) |
| Group Equivariant Convolutional Networks | 1 | 1 | 24 Feb 2016 | not harvested |
| Deep Residual Learning for Image Recognition | 484 | 2 | 10 Dec 2015 | ran 230 of 377 samples (147 unverified; 187 pointer-only for licence) |
Dataset loaders archive 2025-07-28
4 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- PCam
1 variant name, as the archive lists them.
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