Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019
arXiv:1910.12044
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.
6 pages, 3 figures, ICCV 2019 Open Images Workshop
References in corpus (9)
- YOLOv3: An Incremental Improvement
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Cascade R-CNN: Delving into High Quality Object Detection
- Rethinking ImageNet Pre-training
- Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance
- PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track