https://scholars.lib.ntu.edu.tw/handle/123456789/632363
標題: | HARD SAMPLES RECTIFICATION FOR UNSUPERVISED CROSS-DOMAIN PERSON RE-IDENTIFICATION | 作者: | Liu C.-T Lee M.-Y Chen T.-S SHAO-YI CHIEN |
關鍵字: | Computer vision; Person re-identification; Unsupervised learning | 公開日期: | 2021 | 卷: | 2021-September | 起(迄)頁: | 429-433 | 來源出版物: | Proceedings - International Conference on Image Processing, ICIP | 摘要: | Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this paper, we propose a Hard Samples Rectification (HSR) learning scheme which resolves the weakness of original clustering-based methods being vulnerable to the hard positive and negative samples in the target unlabelled dataset. Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative). By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks. © 2021 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125568761&doi=10.1109%2fICIP42928.2021.9506099&partnerID=40&md5=452d24f80027970b7bd9d4a3a3b1222d https://scholars.lib.ntu.edu.tw/handle/123456789/632363 |
ISSN: | 15224880 | DOI: | 10.1109/ICIP42928.2021.9506099 |
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。