Densely Connected Single-Shot Detector | |
Pei Xu3; Xin Zhao2,3; Kaiqi Huang1,2,3 | |
2018-08 | |
会议日期 | 2018-8 |
会议地点 | Beijing, China |
英文摘要 | One-stage object detection approach which utilizes multi-scale feature maps to predict objects is currently the best real-time detector. However, in this approach, the high-resolution feature maps which are responsible for detecting small objects are harder to learn a proper abstraction of objects than the low-resolution feature maps. The problem is that these feature maps have to transform sufficient low-level information to the next layer while learning high-level abstraction. In this paper, we develop a transformation module which adopts the dense structure to simplify the learning problem of high-resolution feature maps. In addition, we utilize the inception module to enrich the representation power of high-resolution feature maps. Extensive experiments on most object detection datasets clearly demonstrate the effectiveness of our method. In particular, on PASCAL VOC 2007/2012, our method outperforms all the existing one-stage methods. Our model based on the VGG-16 network also achieves competitive result on MS COCO. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52052] |
专题 | 智能系统与工程 |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology 2.University of Chinese Academy of Sciences 3.CRIPAC & NLPR,Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Pei Xu,Xin Zhao,Kaiqi Huang. Densely Connected Single-Shot Detector[C]. 见:. Beijing, China. 2018-8. |
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