Multi-network Contrastive Learning Based on Global and Local Representations

TL;DR

This paper introduces a multi-network contrastive learning framework that leverages global and local image features to enhance self-supervised learning, improving performance and training efficiency on benchmark datasets.

Contribution

It proposes a novel multi-network framework that combines global and local representations for contrastive learning, which is a new approach in self-supervised learning.

Findings

Outperforms existing self-supervised methods on benchmark datasets.

Expands sample diversity for contrastive learning, boosting training efficiency.

Effectively captures multi-scale features through multiple networks.

Abstract

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the combination of global and local feature information. This paper proposes a multi-network contrastive learning framework based on global and local representations. We introduce global and local feature information for self-supervised contrastive learning through multiple networks. The model learns feature information at different scales of an image by contrasting the embedding pairs generated by multiple networks. The framework also expands the number of samples used for contrast and improves the training efficiency of the model. Linear evaluation results on three benchmark datasets show that our method outperforms several existing classical self-supervised learning methods.