Title
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
Abstract
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to other transformations, can be used to improve the semantic quality of representations. Specifically, we extend popular SSL methods to a more general framework which we name Equivariant Self-Supervised Learning (E-SSL). In E-SSL, a simple additional pre-training objective encourages equivariance by predicting the transformations applied to the input. We demonstrate E-SSL’s effectiveness empirically on several popular computer vision benchmarks, e.g. improving SimCLR to 72.5% linear probe accuracy on ImageNet. Furthermore, we demonstrate usefulness of E-SSL for applications beyond computer vision; in particular, we show its utility on regression problems in photonics science. Our code, datasets and pre-trained models are available at https://github.com/rdangovs/essl to aid further research in E-SSL.
Year
Venue
Keywords
2022
International Conference on Learning Representations (ICLR)
self-supervised learning,contrastive learning,photonics science
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
8
Name
Order
Citations
PageRank
Rumen Dangovski121.39
Li Jing2165.47
Charlotte Loh300.34
Seungwook Han400.34
Akash Srivastava500.34
Brian Cheung601.01
Pulkit Agrawal700.68
Marin Soljacic801.01