RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense
Positive Supervision
RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense
Positive Supervision
RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian matching provides much sparser supervision, leading to insufficient model training and difficult to achieve optimal results. To address …