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. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Dynamic Warping Network for Semantic Video Segmentation

文献类型：期刊论文

作者Li, Jiangyun1,4; Zhao, Yikai1; He, Xingjian2,3; Zhu, Xinxin2,3; Liu, Jing2
刊名COMPLEXITY
出版日期2021-02-08
卷号2021页码:10
ISSN号1076-2787
DOI10.1155/2021/6680509
通讯作者Li, Jiangyun(leejy@ustb.edu.cn)
英文摘要A major challenge for semantic video segmentation is how to exploit the spatiotemporal information and produce consistent results for a video sequence. Many previous works utilize the precomputed optical flow to warp the feature maps across adjacent frames. However, the imprecise optical flow and the warping operation without any learnable parameters may not achieve accurate feature warping and only bring a slight improvement. In this paper, we propose a novel framework named Dynamic Warping Network (DWNet) to adaptively warp the interframe features for improving the accuracy of warping-based models. Firstly, we design a flow refinement module (FRM) to optimize the precomputed optical flow. Then, we propose a flow-guided convolution (FG-Conv) to achieve the adaptive feature warping based on the refined optical flow. Furthermore, we introduce the temporal consistency loss including the feature consistency loss and prediction consistency loss to explicitly supervise the warped features instead of simple feature propagation and fusion, which guarantees the temporal consistency of video segmentation. Note that our DWNet adopts extra constraints to improve the temporal consistency in the training phase, while no additional calculation and postprocessing are required during inference. Extensive experiments show that our DWNet can achieve consistent improvement over various strong baselines and achieves state-of-the-art accuracy on the Cityscapes and CamVid benchmark datasets.
资助项目Fundamental Research Funds for the China Central Universities of USTB[FRF-DF-19-002] ; Scientific and Technological Innovation Foundation of Shunde Graduate School, USTB[BK20BE014]
WOS研究方向Mathematics ; Science & Technology - Other Topics
语种英语
WOS记录号WOS:000621847600002
出版者WILEY-HINDAWI
资助机构Fundamental Research Funds for the China Central Universities of USTB ; Scientific and Technological Innovation Foundation of Shunde Graduate School, USTB
源URL[http://ir.ia.ac.cn/handle/173211/43985]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者Li, Jiangyun
作者单位1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100083, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100083, Peoples R China
4.Univ Sci & Technol Beijing, Shunde Grad Sch, Foshan 528300, Peoples R China
推荐引用方式
GB/T 7714		 Li, Jiangyun,Zhao, Yikai,He, Xingjian,et al. Dynamic Warping Network for Semantic Video Segmentation[J]. COMPLEXITY,2021,2021:10.
APA Li, Jiangyun,Zhao, Yikai,He, Xingjian,Zhu, Xinxin,&Liu, Jing.(2021).Dynamic Warping Network for Semantic Video Segmentation.COMPLEXITY,2021,10.
MLA Li, Jiangyun,et al."Dynamic Warping Network for Semantic Video Segmentation".COMPLEXITY 2021(2021):10.

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。