Decoupled self-supervised label augmentation for fully-supervised image classification

Gao，Wanshun1; Wu，Meiqing2; Lam，Siew Kei2; Xia，Qihui3; Zou，Jianhua1,4

2022-01-10

10.1016/j.knosys.2021.107605

KNOWLEDGE-BASED SYSTEMS   影响因子和分区

0950-7051

Self-supervised label augmentation has emerged as an effective means to overcome the data scarcity problem for supervised vision tasks. Existing rotation-based self-supervised label augmentation methods either impose or relax the rotation invariance constraint on the primary classifier, which omit necessary supervisory information and may degrade the classification performance depending on the given working data. To overcome this problem, we propose a decoupled self-supervised label augmentation method to enhance the feature representation for fully-supervised image classification. Experimental results on diverse datasets demonstrate that the proposed method consistently outperforms state-of-the-art data augmentation methods. The proposed method is also complementary to conventional data augmentation methods, such as AutoAugment and Fast AutoAugment.

Image classification Multi-task learning Self-supervised label augmentation

SCI ; EI

英语

通讯

WOS:000718126500016

20214511131965

Classification (of information) ; Image enhancement

Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Information Sources and Analysis:903.1

COMPUTER SCIENCE

2-s2.0-85118552022

Scopus

1.School of Electrical and Information Engineering,Xi'an Jiaotong University,Xi'an,No. 28, Xianning West Road,710049,China
2.School of Computer Science and Engineering,Nanyang Technological University,50 Nanyang Avenue,639798,Singapore
3.Southern University of Science and Technology,Shenzhen,1088 Xueyuan Avenue, Nanshan District,518055,China
4.Institute of Guangdong Xi'an Jiaotong University,Foshan,No. 3, Shuxiang East Road,528399,China

Gao，Wanshun,Wu，Meiqing,Lam，Siew Kei,et al. Decoupled self-supervised label augmentation for fully-supervised image classification[J]. KNOWLEDGE-BASED SYSTEMS,2022,235.

Gao，Wanshun,Wu，Meiqing,Lam，Siew Kei,Xia，Qihui,&Zou，Jianhua.(2022).Decoupled self-supervised label augmentation for fully-supervised image classification.KNOWLEDGE-BASED SYSTEMS,235.

Gao，Wanshun,et al."Decoupled self-supervised label augmentation for fully-supervised image classification".KNOWLEDGE-BASED SYSTEMS 235(2022).