# Revisiting DETR Pre-training for Object Detection

Source: [Revisiting DETR Pre-training for Object Detection](<https://www.sota2.com/research/paper/68fa715d1e209131cea50e04>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:02.875Z

Authors: Yan Ma, Weicong Liang, Bohan Chen, Yiduo Hao, Bojian Hou, Xiangyu Yue, Chao Zhang, Yuhui Yuan

Published: 2023-08-02T17:39:30.000Z

## Abstract

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 $\\mathcal{H}$-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 Objects$365$ benchmark. The culmination of these endeavors results in a remarkable AP score of $59.3\\%$ on the COCO val set, outperforming $\\mathcal{H}$-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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.01300>)

[PDF](<https://arxiv.org/pdf/2308.01300.pdf>)