English

Group Equivariant Stand-Alone Self-Attention For Vision

Computer Vision and Pattern Recognition 2021-03-22 v2 Machine Learning

Abstract

We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups. This is achieved by defining positional encodings that are invariant to the action of the group considered. Since the group acts on the positional encoding directly, group equivariant self-attention networks (GSA-Nets) are steerable by nature. Our experiments on vision benchmarks demonstrate consistent improvements of GSA-Nets over non-equivariant self-attention networks.

Keywords

Cite

@article{arxiv.2010.00977,
  title  = {Group Equivariant Stand-Alone Self-Attention For Vision},
  author = {David W. Romero and Jean-Baptiste Cordonnier},
  journal= {arXiv preprint arXiv:2010.00977},
  year   = {2021}
}

Comments

Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021

R2 v1 2026-06-23T18:58:08.373Z