2 papers
cs.CV2026
Generative Verification: Rethinking the Uncertainty Signal for Active Learning of Object Detection
Licheng Zhang, Zheng Gong
Nearly every acquisition function for active object detection shares one arrangement, in that the model being improved is also the model being interrogated. We depart from it. In g…
cs.CV2026
Distance to Class Prototypes: Active Learning for Object Detection
Licheng Zhang, Zheng Gong
Deploying a deep object detector in a new setting is limited less by architecture than by the cost of annotating data from that setting. Active learning lowers the cost by choosing…