Title | ||
---|---|---|
Effective Feature Enhancement and Model Ensemble Strategies in Tiny Object Detection. |
Abstract | ||
---|---|---|
We introduce a novel tiny-object detection network that achieves better accuracy than existing detectors on TinyPerson dataset. It is an end-to-end detection framework developed on PaddlePaddle. A suit of strategies are developed to improve the detectors performance including: 1) data augmentation based on scale-match that aligns the object scales between the existing large-scale dataset and TinyPerson; 2) comprehensive training methods to further improve detection performance by a large margin; 3) model refinement based on the enhanced PAFPN module to fully utilize semantic information; 4) a hierarchical coarse-to-fine ensemble strategy to improve detection performance based on a well-designed model pond. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/978-3-030-68238-5_24 | ECCV Workshops |
Keywords | DocType | Citations |
Data augmentation,Feature pyramid,Model ensemble | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuan Feng | 1 | 0 | 0.68 |
Xiaodi Wang | 2 | 9 | 4.21 |
Ying Xin | 3 | 0 | 2.03 |
Bin Zhang | 4 | 11 | 4.02 |
Jingwei Liu | 5 | 20 | 10.65 |
Mingyuan Mao | 6 | 0 | 0.68 |
Sheng Xu | 7 | 507 | 71.47 |
Baochang Zhang | 8 | 1130 | 93.76 |
Shumin Han | 9 | 0 | 1.69 |