|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM355203162 |
| 003 |
DE-627 |
| 005 |
20231226063840.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3226866
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1183.xml
|
| 035 |
|
|
|a (DE-627)NLM355203162
|
| 035 |
|
|
|a (NLM)37015570
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Chen, Hao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Learning Invariance From Generated Variance for Unsupervised Person Re-Identification
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 07.05.2023
|
| 500 |
|
|
|a Date Revised 07.05.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this article, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Wang, Yaohui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lagadec, Benoit
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Dantcheva, Antitza
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Bremond, Francois
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 6 vom: 05. Juni, Seite 7494-7508
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:6
|g day:05
|g month:06
|g pages:7494-7508
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3226866
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 6
|b 05
|c 06
|h 7494-7508
|