FlowOVD: Learning Generative Latent Flows for Zero-shot Open-vocabulary Detection 事件

FlowOVD: Learning Generative Latent Flows for Zero-shot Open-vocabulary Detection arXiv:2606.00782v1 Announce Type: new Abstract: Open-vocabulary object detection (OVD) has achieved remarkable progress through large-scale vision-language pre-training. Existing methods, however, typically formulate OVD as a discriminative prediction problem, where decoder queries are either static or initialized from encoder features, thus limiting their diversity and flexibility. In this paper, we introduce a g