Contrastive Self-supervised Representation Learning Using Synthetic Data

doi:10.1007/s11633-021-1297-9

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Contrastive Self-supervised Representation Learning Using Synthetic Data
	Dong-Yu She; Kun Xu
发表期刊	International Journal of Automation and Computing
ISSN	1476-8186
	2021
卷号	18 期号:4 页码:556-567
摘要	Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability.Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.
关键词	Self-supervised learning contrastive learning synthetic image convolutional neural network representation learning
DOI	10.1007/s11633-021-1297-9
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/45063
专题	学术期刊_Machine Intelligence Research
作者单位	Beijing National Research Center for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
推荐引用方式 GB/T 7714	Dong-Yu She,Kun Xu. Contrastive Self-supervised Representation Learning Using Synthetic Data[J]. International Journal of Automation and Computing,2021,18(4):556-567.
APA	Dong-Yu She,&Kun Xu.(2021).Contrastive Self-supervised Representation Learning Using Synthetic Data.International Journal of Automation and Computing,18(4),556-567.
MLA	Dong-Yu She,et al."Contrastive Self-supervised Representation Learning Using Synthetic Data".International Journal of Automation and Computing 18.4(2021):556-567.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
IJAC-2020-10-280.pdf（993KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载