Knowledge Commons of Institute of Automation,CAS
Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation | |
Yu Liu![]() ![]() | |
Source Publication | IEEE/CAA Journal of Automatica Sinica
![]() |
ISSN | 2329-9266 |
2023 | |
Volume | 10Issue:3Pages:711-721 |
Abstract | Few-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. |
Keyword | Artificial intelligence computer vision deep convolutional neural network few-shot semantic segmentation |
DOI | 10.1109/JAS.2022.105863 |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://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-SA | View Download |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment