UM  > Faculty of Science and Technology  > DEPARTMENT OF ELECTROMECHANICAL ENGINEERING
Affiliated with RCfalse
Status已發表Published
Fast target-aware learning for few-shot video object segmentation
Yang ZX(楊志新)
2022-08
Source PublicationScience China Information Sciences
ISSN1674-733X
Volume65Issue:8Pages:1-16
Abstract

Few-shot video object segmentation (FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video sequences. The proposed method is trained only on an individual public video object segmentation (VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouTubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile, a high inference speed of approximately 0.13 s per frame is maintained.

KeywordVideo Object Segmentation Few-shot Target-aware Meta Knowledge Bilevel-optimization
DOI10.1007/s11432-021-3396-7
Indexed BySCIE
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic
WOS IDWOS:000833497800007
Scopus ID2-s2.0-85135369630
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF ELECTROMECHANICAL ENGINEERING
Faculty of Science and Technology
Affiliationstate key Laboratory of Internet of things for smart city, and Department of Electromechanical Engineering, Faculty of Science and Technology, University of Macau
Recommended Citation
GB/T 7714
Yang ZX. Fast target-aware learning for few-shot video object segmentation[J]. Science China Information Sciences,2022,65(8):1-16.
APA Yang ZX.(2022).Fast target-aware learning for few-shot video object segmentation.Science China Information Sciences,65(8),1-16.
MLA Yang ZX."Fast target-aware learning for few-shot video object segmentation".Science China Information Sciences 65.8(2022):1-16.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang ZX(楊志新)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang ZX(楊志新)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang ZX(楊志新)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.