Papers › General E(2)-Equivariant Steerable CNNs
General E(2)-Equivariant Steerable CNNs
Maurice Weiler, Gabriele Cesa
The big empirical success of group equivariant networks has led in recent years to the sprouting of a great variety of equivariant network architectures. A particular focus has thereby been on rotation and reflection equivariant CNNs for planar images. Here we give a general description of E(2)-equivariant convolutions in the framework of Steerable CNNs. The theory of Steerable CNNs thereby yields constraints on the convolution kernels which depend on group representations describing the transformation laws of feature spaces. We show that these constraints for arbitrary group representations can be reduced to constraints under irreducible representations. A general solution of the kernel space constraint is given for arbitrary representations of the Euclidean group E(2) and its subgroups. We implement a wide range of previously proposed and entirely new equivariant network architectures and extensively compare their performances. E(2)-steerable convolutions are further shown to yield remarkable gains on CIFAR-10, CIFAR-100 and STL-10 when used as a drop-in replacement for non-equivariant convolutions.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | STL-10 | wrn16/8 D8 D4 D1 | Percentage correct | 90.20 | #34 of 117 | Archive leaderboard | report |
| Image Classification | STL-10 | wrn16/8* D8 D4 D1 | Percentage correct | 89.43 | #38 of 117 | Archive leaderboard | report |
| Image Classification | STL-10 | wrn16/8* D1 D1 D1 | Percentage correct | 88.95 | #39 of 117 | Archive leaderboard | report |
| Image Classification | STL-10 | wrn16/8 D1 D1 D1 | Percentage correct | 88.83 | #40 of 117 | Archive leaderboard | report |
| Image Classification | STL-10 | wrn16/8 | Percentage correct | 87.26 | #47 of 117 | 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
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