Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection

• Published in: arXiv.org
• Main Authors: Wu, Xiongwei, Zhang, Daoxin, Zhu, Jianke, Hoi, Steven C H
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 22.03.2018
• Subjects: Anchors; Cameras; Detectors; Machine learning; Object recognition; Quality

Recent years have witnessed many exciting achievements for object detection using deep learning techniques. Despite achieving significant progresses, most existing detectors are designed to detect objects with relatively low-quality prediction of locations, i.e., often trained with the threshold of Intersection over Union (IoU) set to 0.5 by default, which can yield low-quality or even noisy detections. It remains an open challenge for how to devise and train a high-quality detector that can achieve more precise localization (i.e., IoU\(>\)0.5) without sacrificing the detection performance. In this paper, we propose a novel single-shot detection framework of Bidirectional Pyramid Networks (BPN) towards high-quality object detection, which consists of two novel components: (i) a Bidirectional Feature Pyramid structure for more effective and robust feature representations; and (ii) a Cascade Anchor Refinement to gradually refine the quality of predesigned anchors for more effective training. Our experiments showed that the proposed BPN achieves the best performances among all the single-stage object detectors on both PASCAL VOC and MS COCO datasets, especially for high-quality detections.