Revisiting DETR Pre-training for Object Detection

Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of Transformers while preserving a frozen backbone. Noteworthy advancements in accuracy have been documented in certain studies. Our investigation delved deeply into a representative approach, DETReg, and its performance assessment in the context of emerging models like H-Deformable-DETR. Regrettably, DETReg proves inadequate in enhancing the performance of robust DETR-based models under full data conditions. To dissect the underlying causes, we conduct extensive experiments on COCO and PASCAL VOC probing elements such as the selection of pre-training datasets and strategies for pre-training target generation. By contrast, we employ an optimized approach named Simple Self-training which leads to marked enhancements through the combination of an improved box predictor and the Objects365 benchmark. The culmination of these endeavors results in a remarkable AP score of 59.3% on the COCO val set, outperforming H-Deformable-DETR + Swin-L without pre-training by 1.4%. Moreover, a series of synthetic pre-training datasets, generated by merging contemporary image-to-text(LLaVA) and text-to-image (SDXL) models, significantly amplifies object detection capabilities.