Abstract | ||
---|---|---|
Recent years have witnessed significant advances in deep learning based object detection. Despite being extensively explored, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., they are often trained with the threshold of Intersection over Union (IoU) set as 0.5. This can yield low-quality or even noisy detections. Designing high quality object detectors which have a more precise localization (e.g. IoU > 0.5) remains an open challenge. In this paper, we propose a novel single-shot detection framework called Bidirectional Pyramid Networks (BPN) for high-quality object detection. It comprises two novel components: (i) Bidirectional Feature Pyramid structure and Anchor Refinement (AR). The bidirectional feature pyramid structure aims to use semantic-rich deep layer features to enhance the quality of the shallow layer features, and simultaneously use the spatially-rich shallow layer features to enhance the quality of deep layer features, leading to a stronger representation of both small and large objects for high quality detection. Our anchor refinement scheme gradually refines the quality of pre-designed anchors by learning multi-level regressors, giving more precise localization predictions. We performed extensive experiments on both PASCAL VOC and MSCOCO datasets, and achieved the best performance among all single-shot detectors. The performance was especially superior in the regime of high-quality detection. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neucom.2020.02.116 | Neurocomputing |
Keywords | DocType | Volume |
Object detection,Deep learning,Computer vision,Anchor refinement | Journal | 401 |
ISSN | Citations | PageRank |
0925-2312 | 1 | 0.35 |
References | Authors | |
18 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wu Xiongwei | 1 | 29 | 2.63 |
Doyen Sahoo | 2 | 83 | 9.94 |
Daoxin Zhang | 3 | 1 | 0.35 |
Jianke Zhu | 4 | 1702 | 68.54 |
Steven C. H. Hoi | 5 | 3830 | 174.61 |