Multi-pseudo Regularized Label for Generated Data in Person Re-Identification
Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images (i.e., annotation), the amount of available training data (i.e., real data) is always limited. To produce more data for training a deep netw...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - (2018) vom: 08. Okt.
|
|---|
| 1. Verfasser: |
Huang, Yan
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Xu, Jingsong,
Wu, Qiang,
Zheng, Zhedong,
Zhang, Zhaoxiang,
Zhang, Jian |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2018
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|