Dynamic Instance Domain Adaptation
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain labels are exploited to learn domain-invariant features v...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 01., Seite 4585-4597
|
|---|
| 1. Verfasser: |
Deng, Zhongying
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zhou, Kaiyang,
Li, Da,
He, Junjun,
Song, Yi-Zhe,
Xiang, Tao |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|