arXiv cs.CV
· Papers
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $mathrm{O}(2)$
arXiv:2606.27864v2 Announce Type: replace Abstract: Vision transformers have become a dominant architecture for visual recognition. However, standard models do not explicitly encode the planar symmetries that arise in many vision domains. We introduce a family of vision transformers equivariant to arbitrary discrete su