Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/144247
Title: CRNet : cross-reference networks for few-shot segmentation
Authors: Liu, Weide
Zhang, Chi
Lin, Guosheng
Liu, Fayao
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Liu, W., Zhang, C., Lin, G., & Liu, F. (2020). CRNet : cross-reference networks for few-shot segmentation. Proceedings of 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/CVPR42600.2020.00422
Project: AISG-RP-2018-003 
RG126/17 (S) 
RG22/19 (S) 
Conference: 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Abstract: Over the past few years, state-of-the-art image segmentation algorithms are based on deep convolutional neural networks. To render a deep network with the ability to understand a concept, humans need to collect a large amount of pixel-level annotated data to train the models, which is time-consuming and tedious. Recently, few-shot segmentation is proposed to solve this problem. Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. In this paper, we propose a cross-reference network (CRNet) for few-shot segmentation. Unlike previous works which only predict the mask in the query image, our proposed model concurrently make predictions for both the support image and the query image. With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images, thus helping the few-shot segmentation task. We also develop a mask refinement module to recurrently refine the prediction of the foreground regions. For the k-shot learning, we propose to finetune parts of networks to take advantage of multiple labeled support images. Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.
URI: https://hdl.handle.net/10356/144247
DOI: 10.1109/CVPR42600.2020.00422
Schools: School of Computer Science and Engineering 
Rights: © 2020 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 in other works. The published version is available at: https://doi.org/10.1109/CVPR42600.2020.00422
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
weide 01916.pdf2.42 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 5

134
Updated on Mar 28, 2024

Web of ScienceTM
Citations 5

82
Updated on Oct 30, 2023

Page view(s)

338
Updated on Mar 27, 2024

Download(s) 20

193
Updated on Mar 27, 2024

Google ScholarTM

Check

Altmetric


Plumx

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