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

Source: [Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019](<https://www.sota2.com/research/paper/68fa66901e209131cea10e68>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:52:21.192Z

Authors: Xingyuan Bu, Junran Peng, Changbao Wang, Cunjun Yu, Guoliang Cao

Published: 2019-10-26T10:31:35.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.12044>)

[PDF](<https://arxiv.org/pdf/1910.12044.pdf>)