Recalling Unknowns Without Losing Precision : An Effective Solution to Large Model-Guided Open World Object Detection

Open World Object Detection (OWOD) aims to adapt object detection to an open-world environment, so as to detect unknown objects and learn knowledge incrementally. Existing OWOD methods typically leverage training sets with a relatively small number of known objects. Due to the absence of generic obj...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 34(2025) vom: 18., Seite 729-742
1. Verfasser:	He, Yulin (VerfasserIn)
Weitere Verfasser:	Chen, Wei, Wang, Siqi, Liu, Tianrui, Wang, Meng
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2025
Zugriff auf das übergeordnete Werk:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:	Journal Article