Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining

arXiv:2604.11195v1 Announce Type: cross Abstract: Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and adapting to both base and novel categories in the target domain without target annotations. However, current AOOD methods remain limited by weak cross-domain representations, ambiguity among novel categories, and