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

Abstract

This report demonstrates our solution for the Open Images 2018 Challenge. Based on our detailed analysis on the Open Images Datasets (OID), it is found that there are four typical features: large-scale, hierarchical tag system, severe annotation incompleteness and data imbalance. Considering these characteristics, an amount of strategies are employed, including SNIPER, soft sampling, class-aware sampling (CAS), hierarchical non-maximum suppression (HNMS) and so on. In virtue of these effective strategies, and further using the powerful SENet154 armed with feature pyramid module and deformable ROIalign as the backbone, our best single model could achieve a mAP of 56.9%. After a further ensemble with 9 models, the final mAP is boosted to 62.2% in the public leaderboard (ranked the 2nd place) and 58.6% in the private leaderboard (ranked the 3rd place, slightly inferior to the 1st place by only 0.04 point).

arXiv comment5 pages, 4 figures, ECCV 2018 Open Images workshop

References in corpus (14)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Feature Pyramid Networks for Object Detection
• Deformable Convolutional Networks
• Cascade R-CNN: Delving into High Quality Object Detection
• Path Aggregation Network for Instance Segmentation
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• DetNet: A Backbone network for Object Detection
• Relation Networks for Object Detection
• Acquisition of Localization Confidence for Accurate Object Detection
• SNIPER: Efficient Multi-Scale Training
• Soft Sampling for Robust Object Detection
• Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks

Cited by in corpus (6)

• Soft Sampling for Robust Object Detection
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
• 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
• Dataset balancing can hurt model performance
• Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
• Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019