Task-Aware Weakly Supervised Object Localization With Transformer
Weakly supervised object localization (WSOL) aims to predict both object locations and categories with only image-level class labels. However, most existing methods rely on class-specific image regions for localization, resulting in incomplete object localization. To alleviate this problem, we propo...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 7 vom: 07. Juli, Seite 9109-9121
|
|---|
| 1. Verfasser: |
Meng, Meng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zhang, Tianzhu,
Zhang, Zhe,
Zhang, Yongdong,
Wu, Feng |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|