中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
Mask SSD: An Effective Single-Stage Approach to Object Instance Segmentation

文献类型：期刊论文

作者Zhang, Hui3,4; Tian, Yonglin2,4; Wang, Kunfeng4,5; Zhang, Wensheng1; Wang, Fei-Yue4
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29期号:1页码:2078-2093
关键词Object detection instance segmentation feedback features single-shot detector
ISSN号1057-7149
DOI10.1109/TIP.2019.2947806
通讯作者Wang, Kunfeng(wangkf@mail.buct.edu.cn)
英文摘要We propose Mask SSD, an efficient and effective approach to address the challenging instance segmentation task. Based on a single-shot detector, Mask SSD detects all instances in an image and marks the pixels that belong to each instance. It consists of a detection subnetwork that predicts object categories and bounding box locations, and an instance-level segmentation subnetwork that generates the foreground mask for each instance. In the detection subnetwork, multi-scale and feedback features from different layers are used to better represent objects of various sizes and provide high-level semantic information. Then, we adopt an assistant classification network to guide per-class score prediction, which consists of objectness prior and category likelihood. The instance-level segmentation subnetwork outputs pixel-wise segmentation for each detection while providing the multi-scale and feedback features from different layers as input. These two subnetworks are jointly optimized by a multi-task loss function, which renders Mask SSD direct prediction on detection and segmentation results. We conduct extensive experiments on PASCAL VOC, SBD, and MS COCO datasets to evaluate the performance of Mask SSD. Experimental results verify that as compared with state-of-the-art approaches, our proposed method has a comparable precision with less speed overhead.
资助项目National Key R&D Program of China[2018YFC1704400] ; National Natural Science Foundation of China[U1811463]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000505788600007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key R&D Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/29443]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Wang, Kunfeng
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China
3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
5.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Hui,Tian, Yonglin,Wang, Kunfeng,et al. Mask SSD: An Effective Single-Stage Approach to Object Instance Segmentation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29(1):2078-2093.
APA Zhang, Hui,Tian, Yonglin,Wang, Kunfeng,Zhang, Wensheng,&Wang, Fei-Yue.(2020).Mask SSD: An Effective Single-Stage Approach to Object Instance Segmentation.IEEE TRANSACTIONS ON IMAGE PROCESSING,29(1),2078-2093.
MLA Zhang, Hui,et al."Mask SSD: An Effective Single-Stage Approach to Object Instance Segmentation".IEEE TRANSACTIONS ON IMAGE PROCESSING 29.1(2020):2078-2093.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。