Papers › Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

7 Nov 2022arXiv 2022 11arXiv:2211.03594archive 2025-07-28

Qiang Chen, Jian Wang, Chuchu Han, Shan Zhang, Zexian Li, Xiaokang Chen, Jiahui Chen, Xiaodi Wang, Shuming Han, Gang Zhang, Haocheng Feng, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~\cite{dosovitskiy2020image}, a DETR variant DINO~\cite{zhang2022dino}, and an efficient DETR training method Group DETR~\cite{chen2022group}. The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO. Group DETR v2 achieves 64.5 mAP on COCO test-dev, and establishes a new SoTA on the COCO leaderboard https://paperswithcode.com/sota/object-detection-on-coco

Paper PDF Conference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder Object Object Detection object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Object Detection	COCO test-dev	Group DETR v2	AP50	81.8	#8 of 225	Archive leaderboard	report
Object Detection	COCO test-dev	Group DETR v2	AP75	71.1	#8 of 225	Archive leaderboard	report
Object Detection	COCO test-dev	Group DETR v2	APL	77.1	#8 of 225	Archive leaderboard	report
Object Detection	COCO test-dev	Group DETR v2	APM	67.2	#8 of 225	Archive leaderboard	report
Object Detection	COCO test-dev	Group DETR v2	APS	48.4	#8 of 225	Archive leaderboard	report
Object Detection	COCO test-dev	Group DETR v2	box mAP	64.5	#8 of 225	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Detr Dropout Feedforward Network Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Vision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections