Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-Identification

Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsupervised Re-ID is clustering-based, which generates pseudo labels by clustering and uses the pseudo labels to train a Re...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 14., Seite 6548-6561
1. Verfasser: Wang, Menglin (VerfasserIn)
Weitere Verfasser: Li, Jiachen, Lai, Baisheng, Gong, Xiaojin, Hua, Xian-Sheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM347550738
003 DE-627
005 20231226034106.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2022.3213193  |2 doi 
028 5 2 |a pubmed24n1158.xml 
035 |a (DE-627)NLM347550738 
035 |a (NLM)36240040 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wang, Menglin  |e verfasserin  |4 aut 
245 1 0 |a Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-Identification 
264 1 |c 2022 
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 25.10.2022 
500 |a Date Revised 25.10.2022 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsupervised Re-ID is clustering-based, which generates pseudo labels by clustering and uses the pseudo labels to train a Re-ID model iteratively. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the intra-cluster variance mainly caused by the change of cameras. To address this issue, we propose to split each single cluster into multiple proxies according to camera views. The camera-aware proxies explicitly capture local structures within clusters, by which the intra-ID variance and inter-ID similarity can be better tackled. Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results. The offline association directly associates proxies according to the clustering and splitting results, while the online strategy dynamically associates proxies in terms of up-to-date features to reduce the noise caused by the delayed update of pseudo labels. The combination of two losses enables us to train a desirable Re-ID model. Extensive experiments on three person Re-ID datasets and one vehicle Re-ID dataset show that our proposed approach demonstrates competitive performance with state-of-the-art methods. Code will be available at: https://github.com/Terminator8758/O2CAP 
650 4 |a Journal Article 
700 1 |a Li, Jiachen  |e verfasserin  |4 aut 
700 1 |a Lai, Baisheng  |e verfasserin  |4 aut 
700 1 |a Gong, Xiaojin  |e verfasserin  |4 aut 
700 1 |a Hua, Xian-Sheng  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 31(2022) vom: 14., Seite 6548-6561  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:31  |g year:2022  |g day:14  |g pages:6548-6561 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2022.3213193  |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 31  |j 2022  |b 14  |h 6548-6561