忘記密碼
Chenyu Yang1* Yuntao Chen2* Hao Tian3* Chenxin Tao1 Xizhou Zhu3 Zhaoxiang Zhang2,4 Gao Huang1
Hongyang Li5 Yu Qiao5 Lewei Lu3 Jie Zhou1 Jifeng Dai1,5 ?
1Tsinghua University 2Centre for Artificial Intelligence and Robotics, HKISI CAS 3SenseTime Research 4Institute of Automation, Chinese Academy of Science (CASIA) 5Shanghai Artificial Intelligence Laboratory
{yangcy19, tcx20}@mails.tsinghua.edu.cn, chenyuntao08@gmail.com, tianhao2@senseauto.com
{zhuwalter, luotto}@sensetime.com, zhaoxiang.zhang@ia.ac.cn
{gaohuang, jzhou, daijifeng}@tsinghua.edu.cn, {lihongyang, qiaoyu}@pjlab.org.cn
Abstract
We present a novel bird’s-eye-view (BEV) detector with perspective supervision, which converges faster and better suits modern image backbones. Existing state-of-theart BEV detectors are often tied to certain depth pretrained backbones like VoVNet, hindering the synergy between booming image backbones and BEV detectors. To address this limitation, we prioritize easing the optimization of BEV detectors by introducing perspective view supervision. To this end, we propose a two-stage BEV detector, where proposals from the perspective head are fed into the bird’s-eye-view head for final predictions. To evaluate the effectiveness of our model, we conduct extensive ablation studies focusing on the form of supervision and the generality of the proposed detector. The proposed method is verified with a wide spectrum of traditional and modern image backbones and achieves new SoTA results on the large-scale nuScenes dataset. The code shall be released soon.