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

11/17/2019

∙

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.

READ FULL TEXT

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

PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track

Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019

A framework for robust object multi-detection with a vote aggregation and a cascade filtering

Learning Hough Regression Models via Bridge Partial Least Squares for Object Detection

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

1st Place Solutions for OpenImage2019 – Object Detection and Instance Segmentation

Blocks as geographic discontinuities: The effect of polling place assignment on voting

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

Related Research

PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track

Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019

A framework for robust object multi-detection with a vote aggregation and a cascade filtering

Learning Hough Regression Models via Bridge Partial Least Squares for Object Detection

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

1st Place Solutions for OpenImage2019 – Object Detection and Instance Segmentation

Blocks as geographic discontinuities: The effect of polling place assignment on voting