Relation Matters : Foreground-Aware Graph-Based Relational Reasoning for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) focuses on improving the generalization ability of object detectors via knowledge transfer. Recent advances in DAOD strive to change the emphasis of the adaptation process from global to local in virtue of fine-grained feature alignment methods. However, both...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 03. März, Seite 3677-3694
|
|---|
| 1. Verfasser: |
Chen, Chaoqi
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Jiongcheng,
Zhou, Hong-Yu,
Han, Xiaoguang,
Huang, Yue,
Ding, Xinghao,
Yu, Yizhou |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|