Unsupervised Multi-Class Domain Adaptation : Theory, Algorithms, and Practice
In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 5 vom: 14. Mai, Seite 2775-2792
|
|---|
| 1. Verfasser: |
Zhang, Yabin
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Deng, Bin,
Tang, Hui,
Zhang, Lei,
Jia, Kui |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|