https://scholars.lib.ntu.edu.tw/handle/123456789/632087
標題: | Domain generalized person re-identification via cross-domain episodic learning | 作者: | Lin C.-S Cheng Y.-C YU-CHIANG WANG |
公開日期: | 2020 | 起(迄)頁: | 9727-9732 | 來源出版物: | Proceedings - International Conference on Pattern Recognition | 摘要: | Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts. © 2020 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85110549587&doi=10.1109%2fICPR48806.2021.9413013&partnerID=40&md5=ac58202eb5ccd89b33c89518f4732fe9 https://scholars.lib.ntu.edu.tw/handle/123456789/632087 |
ISSN: | 10514651 | DOI: | 10.1109/ICPR48806.2021.9413013 | SDG/關鍵字: | Arts computing; Benchmark datasets; Domain adaptation; Invariant features; Invariant properties; Learning schemes; Meta learning strategy; Person re identifications; State of the art; Pattern recognition |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。