Unsupervised Part Discovery via Dual Representation Alignment
Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision Transformer can learn instance-level attention without labels,...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 12 vom: 29. Dez., Seite 10597-10613
|
|---|
| 1. Verfasser: |
Xia, Jiahao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Huang, Wenjian,
Xu, Min,
Zhang, Jianguo,
Zhang, Haimin,
Sheng, Ziyu,
Xu, Dong |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2024
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|