Group Equivariant Stand-Alone Self-Attention For VisionDownload PDF

Published: 12 Jan 2021, Last Modified: 22 Oct 2023ICLR 2021 PosterReaders: Everyone
Keywords: group equivariant transformers, group equivariant self-attention, group equivariance, self-attention, transformers
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.
One-sentence Summary: We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Supplementary Material: zip
Code: [![github](/images/github_icon.svg) dwromero/g_selfatt](https://github.com/dwromero/g_selfatt)
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.00977/code)
16 Replies

Loading