Dual Refinement Network for Single-Shot Object Detection | |
Chen, Xingyu2,3; Yang, Xiyuan2; Kong, Shihan2,3; Wu, Zhengxing2,3; Yu, Junzhi1,2,3 | |
2020-03 | |
会议日期 | 2019-5 |
会议地点 | Montreal, Canada |
英文摘要 | Object detection methods fall into two categories, i.e., two-stage and single-stage detectors. The former is characterized by high detection accuracy while the latter usually has a considerable inference speed. Hence, it is imperative to fuse their merits for a better accuracy vs. speed trade-off. To this end, we propose a dual refinement network (DRN) to boost the performance of the single-stage detector. Inheriting from the advantages of two-stage approaches (i.e., two-step regression and accurate features for detection), anchor refinement and feature offset refinement are conducted in a novel anchor-offset detection, where the detection head is comprised of deformable convolutions. Moreover, to leverage contextual information for describing objects, we design a multi-deformable head, in which multiple detection paths with different receptive field sizes devote themselves to detecting objects. Extensive experiments on PASCAL VOC and ImageNet VID datasets are conducted, and we achieve a state-of-the-art detection performance in terms of |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39065] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Wu, Zhengxing; Yu, Junzhi |
作者单位 | 1.Peking University 2.University of Chinese Academy of Sciences 3.Institute of Automation, Chinese Academy of Science |
推荐引用方式 GB/T 7714 | Chen, Xingyu,Yang, Xiyuan,Kong, Shihan,et al. Dual Refinement Network for Single-Shot Object Detection[C]. 见:. Montreal, Canada. 2019-5. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论