TriBYOL: Triplet BYOL for Self-Supervised Representation Learning

TL;DR

TriBYOL introduces a triplet network with a triple-view loss to enhance self-supervised representation learning, especially effective with small batch sizes, reducing computational demands and outperforming existing methods.

Contribution

The paper presents a novel triplet network architecture with a triple-view loss for improved self-supervised learning using small batch sizes.

Findings

Outperforms state-of-the-art methods on multiple datasets with small batches

Requires less computational resources compared to traditional methods

Effective for high-resolution images in real-world scenarios

Abstract

This paper proposes a novel self-supervised learning method for learning better representations with small batch sizes. Many self-supervised learning methods based on certain forms of the siamese network have emerged and received significant attention. However, these methods need to use large batch sizes to learn good representations and require heavy computational resources. We present a new triplet network combined with a triple-view loss to improve the performance of self-supervised representation learning with small batch sizes. Experimental results show that our method can drastically outperform state-of-the-art self-supervised learning methods on several datasets in small-batch cases. Our method provides a feasible solution for self-supervised learning with real-world high-resolution images that uses small batch sizes.