2nd Place Solution in Google AI Open Images Object Detection Track 2019

Cheng Cui; Jianfeng Zhu; Jingwei Liu; Ruoyu Guo; Shumin Han; Xianglong Meng; Xiaodi Wang; Yuan Feng; Yuning Du

REVIEW

2nd Place Solution in Google AI Open Images Object Detection Track 2019

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.07171 v1 pith:WCPBK5C4 submitted 2019-11-17 cs.CV

Ruoyu Guo , Cheng Cui , Yuning Du , Xianglong Meng , Xiaodi Wang , Jingwei Liu , Jianfeng Zhu , Yuan Feng

show 1 more author

Shumin Han

This is my paper

classification cs.CV

keywords detectionobjectgoogleimagesmethodopenplaceresults

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

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.

Discussion (0). Sign in to comment.

Pith tools