Grid R-CNN is a well-performed objection detection framework. It transforms the traditional box offset regression problem into a grid point estimation problem. With the guidance of the grid points, it can obtain high-quality localization results. However, the speed of Grid R-CNN is not so satisfactory. In this technical report we present Grid R-CNN Plus, a better and faster version of Grid R-CNN. We have made several updates that significantly speed up the framework and simultaneously improve the accuracy. On COCO dataset, the Res50-FPN based Grid R-CNN Plus detector achieves an mAP of 40.4%, outperforming the baseline on the same model by 3.0 points with similar inference time. Code is available at https://github.com/STVIR/Grid-R-CNN .
@article{arxiv.1906.05688,
title = {Grid R-CNN Plus: Faster and Better},
author = {Xin Lu and Buyu Li and Yuxin Yue and Quanquan Li and Junjie Yan},
journal= {arXiv preprint arXiv:1906.05688},
year = {2019}
}