Knowledge Exchange Between Domain-Adversarial and Private Networks Improves Open Set Image Classification
Both target-specific and domain-invariant features can facilitate Open Set Domain Adaptation (OSDA). To exploit these features, we propose a Knowledge Exchange (KnowEx) model which jointly trains two complementary constituent networks: (1) a Domain-Adversarial Network (DAdvNet) learning the domain-i...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 14., Seite 5807-5818
|
|---|
| 1. Verfasser: |
Zhou, Haohong
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Azzam, Mohamed,
Zhong, Jian,
Liu, Cheng,
Wu, Si,
Wong, Hau-San |
|---|
| 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 |
|---|