Equivariant Contrastive Learning
arXiv:2111.00899
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.
arXiv commentCamera Ready Revision. ICLR 2022. Discussion: https://openreview.net/forum?id=gKLAAfiytI Code: https://github.com/rdangovs/essl
References in corpus (13)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Bootstrap your own latent: A new approach to self-supervised Learning
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- What Makes for Good Views for Contrastive Learning?
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Group Equivariant Convolutional Networks
- Layer Normalization
- Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis
- Generic 3D Representation via Pose Estimation and Matching
- i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
- Contrastive Learning with Stronger Augmentations
- Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
- Towards Domain-Agnostic Contrastive Learning