Global Cross-Entropy Loss for Deep Face Recognition
Contemporary deep face recognition techniques predominantly utilize the Softmax loss function, designed based on the similarities between sample features and class prototypes. These similarities can be categorized into four types: in-sample target similarity, in-sample non-target similarity, out-sam...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 34(2025) vom: 11., Seite 1672-1685
|
|---|
| 1. Verfasser: |
Zhao, Weisong
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zhu, Xiangyu,
Shi, Haichao,
Zhang, Xiao-Yu,
Zhao, Guoying,
Lei, Zhen |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2025
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|