CASIA OpenIR  > 学术期刊  > IEEE/CAA Journal of Automatica Sinica
Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation
Yu Liu; Bin Jiang; Jiaming Xu
Source PublicationIEEE/CAA Journal of Automatica Sinica
ISSN2329-9266
2023
Volume10Issue:3Pages:711-721
AbstractFew-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars. It remains a challenge because of large intra-class variations between the support and query images. Existing approaches utilize 4D convolutions to mine semantic correspondence between the support and query images. However, they still suffer from heavy computation, sparse correspondence, and large memory. We propose axial assembled correspondence network (AACNet) to alleviate these issues. The key point of AACNet is the proposed axial assembled 4D kernel, which constructs the basic block for semantic correspondence encoder (SCE). Furthermore, we propose the deblurring equations to provide more robust correspondence for the aforementioned SCE and design a novel fusion module to mix correspondences in a learnable manner. Experiments on PASCAL-5i reveal that our AACNet achieves a mean intersection-over-union score of 65.9% for 1-shot segmentation and 70.6% for 5-shot segmentation, surpassing the state-of-the-art method by 5.8% and 5.0% respectively.
KeywordArtificial intelligence computer vision deep convolutional neural network few-shot semantic segmentation
DOI10.1109/JAS.2022.105863
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/51183
Collection学术期刊_IEEE/CAA Journal of Automatica Sinica
Recommended Citation
GB/T 7714
Yu Liu,Bin Jiang,Jiaming Xu. Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation[J]. IEEE/CAA Journal of Automatica Sinica,2023,10(3):711-721.
APA Yu Liu,Bin Jiang,&Jiaming Xu.(2023).Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation.IEEE/CAA Journal of Automatica Sinica,10(3),711-721.
MLA Yu Liu,et al."Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation".IEEE/CAA Journal of Automatica Sinica 10.3(2023):711-721.
Files in This Item: Download All
File Name/Size DocType Version Access License
JAS-2022-0843.pdf(3290KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu Liu]'s Articles
[Bin Jiang]'s Articles
[Jiaming Xu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu Liu]'s Articles
[Bin Jiang]'s Articles
[Jiaming Xu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu Liu]'s Articles
[Bin Jiang]'s Articles
[Jiaming Xu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: JAS-2022-0843.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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