Timezone: »

ReSSL: Relational Self-Supervised Learning with Weak Augmentation
Mingkai Zheng · Shan You · Fei Wang · Chen Qian · Changshui Zhang · Xiaogang Wang · Chang Xu

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of 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 introduced 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. Moreover, to boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. Experimental results show that our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency.

Author Information

Mingkai Zheng (University of Sydney)
Shan You
Fei Wang (SenseTime)
Chen Qian (SenseTime)
Changshui Zhang (Tsinghua University)
Xiaogang Wang (The Chinese University of Hong Kong)
Chang Xu (The University of Sydney)

More from the Same Authors