Complementary Pseudo Labels for Unsupervised Domain Adaptation On Person Re-Identification
In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing methods are primary to use pseudo labels to alleviate this proble...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 08., Seite 2898-2907
|
|---|
| 1. Verfasser: |
Feng, Hao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Chen, Minghao,
Hu, Jinming,
Shen, Dong,
Liu, Haifeng,
Cai, Deng |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2021
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|