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.
@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