Weak Augmentation Guided Relational Self-Supervised Learning

TL;DR

This paper introduces ReSSL, a relational self-supervised learning framework that models relationships between instances using pairwise similarities, employing weak augmentations and momentum strategies to improve visual representation learning.

Contribution

ReSSL is a novel SSL paradigm that focuses on instance relationships, utilizing a relation metric based on pairwise similarities and incorporating strategies for robustness and efficiency.

Findings

ReSSL outperforms state-of-the-art methods across various architectures.

Weak augmentations improve the reliability of relation modeling.

Momentum strategy enhances training efficiency and performance.

Abstract

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduce a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. To boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. The designed asymmetric predictor head and an InfoNCE warm-up strategy enhance the robustness to hyper-parameters and benefit the resulting performance. Experimental results show that our proposed ReSSL substantially outperforms the state-of-the-art methods across different network architectures, including various lightweight networks (\eg, EfficientNet and MobileNet).