DEYO: DETR with YOLO for End-to-End Object Detection

arXiv:2402.16370v1 Announce Type: new
Abstract: The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an inadequately pre-trained neck for DETRs. Additionally, the instability of matching in the early stages of training engenders inconsistencies in the optimization objectives of DETRs. To address these issues, we have devised an innovative training methodology termed step-by-step training. Specifically, in the …

arxiv cs.cv detection detr end-to-end object detection type yolo