Found missing semantics: Supplemental prototype network for few-shot semantic segmentation

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Chen Liang, Shuang Bai
{"title":"Found missing semantics: Supplemental prototype network for few-shot semantic segmentation","authors":"Chen Liang,&nbsp;Shuang Bai","doi":"10.1016/j.cviu.2024.104191","DOIUrl":null,"url":null,"abstract":"<div><div>Few-shot semantic segmentation alleviates the problem of massive data requirements and high costs in semantic segmentation tasks. By learning from support set, few-shot semantic segmentation can segment new classes. However, existing few-shot semantic segmentation methods suffer from information loss during the process of mask average pooling. To address this problem, we propose a supplemental prototype network (SPNet). The SPNet aggregates the lost information from global prototypes to create a supplemental prototype, which enhances the segmentation performance for the current class. In addition, we utilize mutual attention to enhance the similarity between the support and the query feature maps, allowing the model to better identify the target to be segmented. Finally, we introduce a Self-correcting auxiliary, which utilizes the data more effectively to improve segmentation accuracy. We conducted extensive experiments on PASCAL-5i and COCO-20i, which demonstrated the effectiveness of SPNet. And our method achieved state-of-the-art results in the 1-shot and 5-shot semantic segmentation settings.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"249 ","pages":"Article 104191"},"PeriodicalIF":4.3000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002728","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Few-shot semantic segmentation alleviates the problem of massive data requirements and high costs in semantic segmentation tasks. By learning from support set, few-shot semantic segmentation can segment new classes. However, existing few-shot semantic segmentation methods suffer from information loss during the process of mask average pooling. To address this problem, we propose a supplemental prototype network (SPNet). The SPNet aggregates the lost information from global prototypes to create a supplemental prototype, which enhances the segmentation performance for the current class. In addition, we utilize mutual attention to enhance the similarity between the support and the query feature maps, allowing the model to better identify the target to be segmented. Finally, we introduce a Self-correcting auxiliary, which utilizes the data more effectively to improve segmentation accuracy. We conducted extensive experiments on PASCAL-5i and COCO-20i, which demonstrated the effectiveness of SPNet. And our method achieved state-of-the-art results in the 1-shot and 5-shot semantic segmentation settings.
发现丢失的语义:用于少量语义分割的补充原型网络
少量语义分割缓解了语义分割任务中的海量数据需求和高成本问题。通过从支持集学习,少量语义分割可以分割出新的类别。然而,现有的几次语义分割方法在掩码平均池化过程中存在信息丢失问题。为了解决这个问题,我们提出了一种补充原型网络(SPNet)。SPNet 汇集了全局原型丢失的信息,创建了一个补充原型,从而提高了当前类别的分割性能。此外,我们还利用相互关注来增强支持特征图和查询特征图之间的相似性,使模型能够更好地识别待分割目标。最后,我们引入了自校正辅助工具,它能更有效地利用数据来提高分割准确性。我们在 PASCAL-5i 和 COCO-20i 上进行了大量实验,证明了 SPNet 的有效性。我们的方法在 1 次和 5 次语义分割设置中都取得了一流的结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信