2nd Place Solution in Google AI Open Images Object Detection Track 2019
2nd Place Solution in Google AI Open Images Object Detection Track 2019
We present an object detection framework based on PaddlePaddle. We put all the strategies together (multi-scale training, FPN, Cascade, Dcnv2, Non-local, libra loss) based on ResNet200-vd backbone. Our model score on public leaderboard comes to 0.6269 with single scale test. We proposed a new voting method called top-k voting-nms, based on the SoftNMS detection results. The voting method helps us merge all the models' results more easily and achieve 2nd place in the Google AI Open Images Object Detection Track 2019.
Shumin Han、Xianglong Meng、Jianfeng Zhu、Jingwei Liu、Ruoyu Guo、Yuan Feng、Xiaodi Wang、Yuning Du、Cheng Cui
计算技术、计算机技术
Shumin Han,Xianglong Meng,Jianfeng Zhu,Jingwei Liu,Ruoyu Guo,Yuan Feng,Xiaodi Wang,Yuning Du,Cheng Cui.2nd Place Solution in Google AI Open Images Object Detection Track 2019[EB/OL].(2019-11-17)[2025-08-10].https://arxiv.org/abs/1911.07171.点此复制
评论