Learning Invariance From Generated Variance for Unsupervised Person Re-Identification
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...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 6 vom: 05. Juni, Seite 7494-7508
|
|---|
| 1. Verfasser: |
Chen, Hao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Wang, Yaohui,
Lagadec, Benoit,
Dantcheva, Antitza,
Bremond, Francois |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|