Unsupervised Long-Term Person Re-Identification with Clothes Change
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929218567274496 |
|---|---|
| author | Li, Mingkun Cheng, Shupeng Xu, Peng Zhu, Xiatian Li, Chun-Guang Guo, Jun |
| author_facet | Li, Mingkun Cheng, Shupeng Xu, Peng Zhu, Xiatian Li, Chun-Guang Guo, Jun |
| contents | We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment. Most existing re-id methods artificially assume the clothes of every single person to be stationary across space and time. This condition is mostly valid for short-term re-id scenarios since an average person would often change the clothes even within a single day. To alleviate this assumption, several recent works have introduced the clothes change facet to re-id, with a focus on supervised learning person identity discriminative representation with invariance to clothes changes. Taking a step further towards this long-term re-id direction, we further eliminate the requirement of person identity labels, as they are significantly more expensive and more tedious to annotate in comparison to short-term person re-id datasets. Compared to conventional unsupervised short-term re-id, this new problem is drastically more challenging as different people may have similar clothes whilst the same person can wear multiple suites of clothes over different locations and times with very distinct appearance. To overcome such obstacles, we introduce a novel Curriculum Person Clustering (CPC) method that can adaptively regulate the unsupervised clustering criterion according to the clustering confidence. Experiments on three long-term person re-id datasets show that our CPC outperforms SOTA unsupervised re-id methods and even closely matches the supervised re-id models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_03087 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Unsupervised Long-Term Person Re-Identification with Clothes Change Li, Mingkun Cheng, Shupeng Xu, Peng Zhu, Xiatian Li, Chun-Guang Guo, Jun Computer Vision and Pattern Recognition We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment. Most existing re-id methods artificially assume the clothes of every single person to be stationary across space and time. This condition is mostly valid for short-term re-id scenarios since an average person would often change the clothes even within a single day. To alleviate this assumption, several recent works have introduced the clothes change facet to re-id, with a focus on supervised learning person identity discriminative representation with invariance to clothes changes. Taking a step further towards this long-term re-id direction, we further eliminate the requirement of person identity labels, as they are significantly more expensive and more tedious to annotate in comparison to short-term person re-id datasets. Compared to conventional unsupervised short-term re-id, this new problem is drastically more challenging as different people may have similar clothes whilst the same person can wear multiple suites of clothes over different locations and times with very distinct appearance. To overcome such obstacles, we introduce a novel Curriculum Person Clustering (CPC) method that can adaptively regulate the unsupervised clustering criterion according to the clustering confidence. Experiments on three long-term person re-id datasets show that our CPC outperforms SOTA unsupervised re-id methods and even closely matches the supervised re-id models. |
| title | Unsupervised Long-Term Person Re-Identification with Clothes Change |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2202.03087 |