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

10/26/2019
by   Xingyuan Bu, et al.
0

This report details our solution to the Google AI Open Images Challenge 2019 Object Detection Track. Based on our detailed analysis on the Open Images dataset, it is found that there are four typical features: large-scale, hierarchical tag system, severe annotation incompleteness and data imbalance. Considering these characteristics, many strategies are employed, including larger backbone, distributed softmax loss, class-aware sampling, expert model, and heavier classifier. In virtue of these effective strategies, our best single model could achieve a mAP of 61.90. After ensemble, the final mAP is boosted to 67.17 in the public leaderboard and 64.21 in the private leaderboard, which earns 3rd place in the Open Images Challenge 2019.

READ FULL TEXT

page 1

page 3

research
10/15/2018

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

This report demonstrates our solution for the Open Images 2018 Challenge...
research
09/04/2018

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

We present a large-scale object detection system by team PFDet. Our syst...
research
11/17/2019

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

We present an object detection framework based on PaddlePaddle. We put a...
research
05/18/2020

Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels

Training with more data has always been the most stable and effective wa...
research
06/28/2020

DHARI Report to EPIC-Kitchens 2020 Object Detection Challenge

In this report, we describe the technical details of oursubmission to th...
research
12/12/2019

Learning Effective Visual Relationship Detector on 1 GPU

We present our winning solution to the Open Images 2019 Visual Relations...
research
11/27/2018

Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects

Efficient and reliable methods for training of object detectors are in h...

Please sign up or login with your details

Forgot password? Click here to reset