Knowledge Commons of Institute of Automation,CAS
RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation | |
Wang, Shaoru1,4; Gong, Yongchao2; Xing, Junliang1; Huang, Lichao2; Huang, Chang2; Hu, Weiming1,3,4 | |
2020-02 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议日期 | 2020-2 |
会议地点 | New York |
摘要 | Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previous work. This paper presents RDSNet, a novel deep architecture for reciprocal object detection and instance segmentation. To reciprocate these two tasks, we design a two-stream structure to learn features on both the object level (i.e., bounding boxes) and the pixel level (i.e., instance masks) jointly. Within this structure, information from the two streams is fused alternately, namely information on the object level introduces the awareness of instance and translation variance to the pixel level, and information on the pixel level refines the localization accuracy of objects on the object level in return. Specifically, a correlation module and a cropping module are proposed to yield instance masks, as well as a mask based boundary refinement module for more accurate bounding boxes. Extensive experimental analyses and comparisons on the COCO dataset demonstrate the effectiveness and efficiency of RDSNet. The source code is available at https://github.com/wangsr126/RDSNet. |
关键词 | 目标检测 实例分割 |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[U1636218] |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52414 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Xing, Junliang |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.Horizon Robotics Inc. 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Shaoru,Gong, Yongchao,Xing, Junliang,et al. RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
AAAI2020-RDSNet-came(1860KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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