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
Cite
@article{arxiv.2211.03594,
title = {Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining},
author = {Qiang Chen and Jian Wang and Chuchu Han and Shan Zhang and Zexian Li and Xiaokang Chen and Jiahui Chen and Xiaodi Wang and Shuming Han and Gang Zhang and Haocheng Feng and Kun Yao and Junyu Han and Errui Ding and Jingdong Wang},
journal= {arXiv preprint arXiv:2211.03594},
year = {2022}
}
Comments
Tech report, 3 pages. We establishes a new SoTA (64.5 mAP) on the COCO test-dev