DOMAIN ADAPTING ABILITY OF SELF-SUPERVISED LEARNING FOR FACE RECOGNITION

Chun Hsien Lin, Bing-Fei Wu

研究成果: Conference contribution同行評審

1 引文 斯高帕斯(Scopus)

摘要

Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the learned models degenerate in a testing scenario (target domain). In face recognition tasks, classes in two domains are usually different, so classical domain adaptation approaches, assuming there are shared classes in domains, may not be reasonable solutions for this problem. In this paper, self-supervised learning is adopted to learn a better embedding space where the subjects in target domain are more distinguishable. The learning goal is maximizing the similarity between the embeddings of each image and its mirror in both domains. The experiments show its competitive results compared with prior works. To know the reason why it can achieve such performance, we further discuss how this approach affects the learning of embeddings.

原文English
主出版物標題2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
發行者IEEE Computer Society
頁面479-483
頁數5
ISBN(電子)9781665441155
DOIs
出版狀態Published - 2021
事件2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
持續時間: 19 9月 202122 9月 2021

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2021-September
ISSN(列印)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
國家/地區United States
城市Anchorage
期間19/09/2122/09/21

指紋

深入研究「DOMAIN ADAPTING ABILITY OF SELF-SUPERVISED LEARNING FOR FACE RECOGNITION」主題。共同形成了獨特的指紋。

引用此