Mountchicken
commented
2 months ago Hi @xiyangyang99 Indeed, DETR-based models face significant deployment and speed challenges, and we are trying to optimize them. Yet from the perspective of open-set detection performance, both GroundingDINO and T-Rex deliver remarkably better results.
groundingdino和本文类似，但是在工程运用上，不好落地，推理速度不像yolo-world那般快。transformer不好加速推理。跨模态方式的文本加载方式在加速上处理较为麻烦。