Please use this identifier to cite or link to this item:
Title: CANet : class-agnostic segmentation networks with iterative refinement and attentive few-shot learning
Authors: Zhang, Chi
Lin, Guosheng
Liu, Fayao
Yao, Rui
Shen, Chunhua
Keywords: Engineering::Computer science and engineering
Issue Date: 2019
Source: Zhang, C., Lin, G., Liu, F., Yao, R., & Shen, C. (2019). CANet : class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR.2019.00536
Project: AISG-RP-2018-003 
RG126/17 (S) 
Conference: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Abstract: Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only make predictions within a set of pre-defined classes. In this paper, we present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Our network consists of a two-branch dense comparison module which performs multi-level feature comparison between the support image and the query image, and an iterative optimization module which iteratively refines the predicted results. Furthermore, we introduce an attention mechanism to effectively fuse information from multiple support examples under the setting of k-shot learning. Experiments on PASCAL VOC 2012 show that our method achieves a mean Intersection-over-Union score of 55.4% for 1-shot segmentation and 57.1% for 5-shot segmentation, outperforming state-of-the-art methods by a large margin of 14.6% and 13.2%, respectively.
DOI: 10.1109/CVPR.2019.00536
Schools: School of Computer Science and Engineering 
Rights: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
gusoheng paper1 cvpr 2019.pdf1.39 MBAdobe PDFThumbnail

Citations 1

Updated on May 21, 2024

Web of ScienceTM
Citations 1

Updated on Oct 23, 2023

Page view(s)

Updated on Jun 12, 2024

Download(s) 20

Updated on Jun 12, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.