Set Discrimination Contrastive Learning

Duong Hoang Le, Binh-Son Hua

Keywords: self-supervised learning, contrastive learning

Abstract: In this work, we propose a self-supervised contrastive learning method that integrates the concept of set-based feature learning. The main idea of our method is to randomly construct sets of instances in a mini-batch and then learn to contrast the set representations. Inspired by set-based feature learning, we aggregate set features from individual sample features by a symmetric function. To improve the effectiveness of our set-based contrastive learning, we propose a set construction scheme built upon sample permutation in a mini-batch that allows a sample to appear in multiple sets, which naturally ensures common features among sets by construction. Our set construction scheme also increases both the number of positive and negative sets in a mini-batch, leading to better representation learning. We demonstrate the robustness of our method by seamlessly integrating it into existing contrastive learning methods such as SimCLR and MoCo. Extensive experiments demonstrate that our method consistently improves the performance of these contrastive learning methods in various datasets and downstream tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

TL;DR: We propose a method that integrates the concept of set representation learning to improve self-supervised visual representation learning

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning