Category-Aware Siamese Learning Network for Few-Shot Segmentation

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Hui Sun, Ziyan Zhang, Lili Huang, Bo Jiang, Bin Luo
{"title":"Category-Aware Siamese Learning Network for Few-Shot Segmentation","authors":"Hui Sun, Ziyan Zhang, Lili Huang, Bo Jiang, Bin Luo","doi":"10.1007/s12559-024-10273-5","DOIUrl":null,"url":null,"abstract":"<p>Few-shot segmentation (FS) which aims to segment unseen query image based on a few annotated support samples is an active problem in computer vision and multimedia field. It is known that the core issue of FS is how to leverage the annotated information from the support images to guide query image segmentation. Existing methods mainly adopt Siamese Convolutional Neural Network (SCNN) which first encodes both support and query images and then utilizes the masked Global Average Pooling (GAP) to facilitate query image pixel-level representation and segmentation. However, this pipeline generally fails to fully exploit the category/class coherent information between support and query images. <i>For FS task, one can observe that both support and query images share the same category information</i>. This inherent property provides an important cue for FS task. However, previous methods generally fail to fully exploit it for FS task. To overcome this limitation, in this paper, we propose a novel Category-aware Siamese Learning Network (CaSLNet) to encode both support and query images. The proposed CaSLNet conducts <i>Category Consistent Learning (CCL)</i> for both support images and query images and thus can achieve the information communication between support and query images more sufficiently. Comprehensive experimental results on several public datasets demonstrate the advantage of our proposed CaSLNet. Our code is publicly available at https://github.com/HuiSun123/CaSLN.</p>","PeriodicalId":51243,"journal":{"name":"Cognitive Computation","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cognitive Computation","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s12559-024-10273-5","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 segmentation (FS) which aims to segment unseen query image based on a few annotated support samples is an active problem in computer vision and multimedia field. It is known that the core issue of FS is how to leverage the annotated information from the support images to guide query image segmentation. Existing methods mainly adopt Siamese Convolutional Neural Network (SCNN) which first encodes both support and query images and then utilizes the masked Global Average Pooling (GAP) to facilitate query image pixel-level representation and segmentation. However, this pipeline generally fails to fully exploit the category/class coherent information between support and query images. For FS task, one can observe that both support and query images share the same category information. This inherent property provides an important cue for FS task. However, previous methods generally fail to fully exploit it for FS task. To overcome this limitation, in this paper, we propose a novel Category-aware Siamese Learning Network (CaSLNet) to encode both support and query images. The proposed CaSLNet conducts Category Consistent Learning (CCL) for both support images and query images and thus can achieve the information communication between support and query images more sufficiently. Comprehensive experimental results on several public datasets demonstrate the advantage of our proposed CaSLNet. Our code is publicly available at https://github.com/HuiSun123/CaSLN.

Abstract Image

分类感知连体学习网络用于少镜头分割
少镜头分割(FS)的目的是根据少数有注释的支持样本来分割未见的查询图像,它是计算机视觉和多媒体领域的一个活跃问题。众所周知,FS 的核心问题是如何利用支持图像中的注释信息来指导查询图像的分割。现有的方法主要采用连体卷积神经网络(SCNN),它首先对支持图像和查询图像进行编码,然后利用掩码全局平均池化(GAP)来促进查询图像像素级的表示和分割。然而,这种方法通常无法充分利用支持图像和查询图像之间的类别/类一致性信息。在 FS 任务中,我们可以观察到支持图像和查询图像共享相同的类别信息。这一固有属性为 FS 任务提供了重要线索。然而,以往的方法通常无法在 FS 任务中充分利用这一特性。为了克服这一局限性,我们在本文中提出了一种新颖的类别感知连体学习网络(CaSLNet)来对支持图像和查询图像进行编码。所提出的 CaSLNet 对支持图像和查询图像都进行了类别一致学习(CCL),因此能更充分地实现支持图像和查询图像之间的信息沟通。在多个公开数据集上的综合实验结果证明了我们提出的 CaSLNet 的优势。我们的代码可在 https://github.com/HuiSun123/CaSLN 公开获取。
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
Cognitive Computation
Cognitive Computation COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-NEUROSCIENCES
CiteScore
9.30
自引率
3.70%
发文量
116
审稿时长
>12 weeks
期刊介绍: Cognitive Computation is an international, peer-reviewed, interdisciplinary journal that publishes cutting-edge articles describing original basic and applied work involving biologically-inspired computational accounts of all aspects of natural and artificial cognitive systems. It provides a new platform for the dissemination of research, current practices and future trends in the emerging discipline of cognitive computation that bridges the gap between life sciences, social sciences, engineering, physical and mathematical sciences, and humanities.
×
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