UniDetector : Towards Universal Object Detection with Heterogeneous Supervision

In this paper, we formally address universal object detection, which aims to detect every category in every scene. The dependence on human annotations, the limited visual information, and the novel categories in open world severely restrict the universality of detectors. We propose UniDetector, a un...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 11. Juni
1. Verfasser: Wang, Zhenyu (VerfasserIn)
Weitere Verfasser: Li, Yali, Chen, Xi, Lim, Ser-Nam, Torralba, Antonio, Zhao, Hengshuang, Wang, Shengjin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article