Jun-Tao Cheng

RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection

RT-DETR-World is proposed, a compact DETR-style detector that transfers the rich semantics conveyed by descriptions during training while retaining lightweight query--text matching at inference, and Relation-Aware Negative Relaxation (RNR) is proposed, which uses teacher-derived semantic similarities to relax related n...