Weak Augmentation Guided Relational Self-Supervised Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Mingkai, You, Shan, Wang, Fei, Qian, Chen, Zhang, Changshui, Wang, Xiaogang, Xu, Chang
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914819633840128
author Zheng, Mingkai
You, Shan
Wang, Fei
Qian, Chen
Zhang, Changshui
Wang, Xiaogang
Xu, Chang
author_facet Zheng, Mingkai
You, Shan
Wang, Fei
Qian, Chen
Zhang, Changshui
Wang, Xiaogang
Xu, Chang
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2203_08717
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Weak Augmentation Guided Relational Self-Supervised Learning
Zheng, Mingkai
You, Shan
Wang, Fei
Qian, Chen
Zhang, Changshui
Wang, Xiaogang
Xu, Chang
Computer Vision and Pattern Recognition
Machine Learning
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).
title Weak Augmentation Guided Relational Self-Supervised Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2203.08717