• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Wang, Wenjian (Wang, Wenjian.) | Duan, Lijuan (Duan, Lijuan.) (Scholars:段立娟) | En, Qing (En, Qing.) | Zhang, Baochang (Zhang, Baochang.) | Liang, Fangfang (Liang, Fangfang.)

Indexed by:

EI Scopus SCIE

Abstract:

Few-shot semantic segmentation aims to segment new objects in the image with limited annotations. Typically, in metric-based few-shot learning, the expression of categories is obtained by averaging global support object information. However, a single prototype cannot accurately describe a category. Meanwhile, simple foreground averaging operations also ignore the dependencies between objects and their surroundings. In this paper, we propose a novel Transformer-based Prototype Search Network (TPSN) for few-shot segmentation. We use the transformer encoder to integrate information between different image regions and then use the decoder to express a category in terms of multiple prototypes. The multi-prototype approach can effectively alleviate the feature fluctuation caused by limited annotation data. Moreover, we use adaptive prototype search during multi-prototype extraction instead of the ordinary averaging operation compared with the previous few-shot prototype framework. This helps the network integrate the different image regions' information and fuse object features with their dependent background information, obtaining more reasonable prototype expressions. In addition, to encourage the category's prototypes to focus on different parts and maintain consistency in high-level semantics, we use the diversity and consistency loss to constrain the multi-prototype training. Experiments show that our algorithm achieves state-of-the-art performance in few-shot segmentation on two datasets: PASCAL-5(i) and COCO-20(i).

Keyword:

Multiple prototypes Few-shot learning Vision transformer Semantic segmentation

Author Community:

  • [ 1 ] [Wang, Wenjian]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 2 ] [Duan, Lijuan]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China
  • [ 3 ] [Wang, Wenjian]Beijing Key Lab Trusted Comp, Beijing, Peoples R China
  • [ 4 ] [Duan, Lijuan]Beijing Key Lab Trusted Comp, Beijing, Peoples R China
  • [ 5 ] [Wang, Wenjian]Natl Engn Lab Key Technol Informat Secur Level Pro, Beijing, Peoples R China
  • [ 6 ] [Duan, Lijuan]Natl Engn Lab Key Technol Informat Secur Level Pro, Beijing, Peoples R China
  • [ 7 ] [Zhang, Baochang]Beihang Univ, Inst Artificial Intelligence, Beijing, Peoples R China
  • [ 8 ] [En, Qing]Carleton Univ, Sch Comp Sci, Artificialtemp Intelligence & Machine Learning AIM, Ottawa, ON K1S 5B6, Canada
  • [ 9 ] [Liang, Fangfang]Hebei Agr Univ, Hebei Key Lab Agr Big Data, Baoding, Peoples R China

Reprint Author's Address:

Show more details

Related Keywords:

Related Article:

Source :

COMPUTERS & ELECTRICAL ENGINEERING

ISSN: 0045-7906

Year: 2022

Volume: 103

4 . 3

JCR@2022

4 . 3 0 0

JCR@2022

ESI Discipline: COMPUTER SCIENCE;

ESI HC Threshold:46

JCR Journal Grade:2

CAS Journal Grade:3

Cited Count:

WoS CC Cited Count: 9

SCOPUS Cited Count: 14

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 6

Affiliated Colleges:

Online/Total:547/5412077
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.