Papers › Group Equivariant Convolutional Networks

Group Equivariant Convolutional Networks

24 Feb 2016arXiv:1602.07576archive 2025-07-28

Taco S. Cohen, Max Welling

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and rotations. G-CNNs achieve state of the art results on CIFAR10 and rotated MNIST.

PaperPDFCode

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

Code

adambielski/pytorch-gconv-experiments mentioned 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 Tumour ClassificationColorectal Gland Segmentation:Multi-tissue Nucleus SegmentationRotated MNIST

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Breast Tumour Classification PCam G-CNN (C4) AUC 0.964 #6 of 16 Archive leaderboard report
Colorectal Gland Segmentation: CRAG G-CNN (C4) Dice 0.856 #8 of 15 Archive leaderboard report
Colorectal Gland Segmentation: CRAG G-CNN (C4) F1-score 0.833 #8 of 15 Archive leaderboard report
Colorectal Gland Segmentation: CRAG G-CNN (C4) Hausdorff Distance (mm) 170.4 #8 of 15 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar G-CNN (C4) Dice 0.793 #15 of 18 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar G-CNN (C4) Hausdorff Distance (mm) 49.0 #15 of 18 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.

Methods

Convolution

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