语义分割的自监督少镜头学习:一种无标注的方法

Sanaz Karimijafarbigloo, Reza Azad, D. Merhof
{"title":"语义分割的自监督少镜头学习:一种无标注的方法","authors":"Sanaz Karimijafarbigloo, Reza Azad, D. Merhof","doi":"10.48550/arXiv.2307.14446","DOIUrl":null,"url":null,"abstract":"Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at \\href{https://github.com/mindflow-institue/annotation_free_fewshot}{\\textcolor{magenta}{GitHub}}.","PeriodicalId":344481,"journal":{"name":"PRIME@MICCAI","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach\",\"authors\":\"Sanaz Karimijafarbigloo, Reza Azad, D. Merhof\",\"doi\":\"10.48550/arXiv.2307.14446\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at \\\\href{https://github.com/mindflow-institue/annotation_free_fewshot}{\\\\textcolor{magenta}{GitHub}}.\",\"PeriodicalId\":344481,\"journal\":{\"name\":\"PRIME@MICCAI\",\"volume\":\"34 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"PRIME@MICCAI\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2307.14446\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"PRIME@MICCAI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2307.14446","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

少镜头语义分割(FSS)在医学图像分析领域提供了巨大的潜力,可以在有限的训练数据下实现准确的目标分割。然而,现有的FSS技术严重依赖于注释的语义类,由于注释的稀缺性,使得它们不适合医学图像。为了解决这一挑战,提出了多项贡献:首先,受光谱分解方法的启发,将图像分解问题重新定义为图划分任务。从自监督网络的特征亲和矩阵出发,分析拉普拉斯矩阵的特征向量,从支持图像中估计感兴趣对象的分布。其次,我们提出了一个新的不依赖于任何注释的自监督FSS框架。相反,它利用从支持图像中获得的特征向量自适应地估计查询掩码。这种方法消除了手动注释的需要,使其特别适合具有有限注释数据的医学图像。第三,为了进一步增强基于支持图像提供的信息对查询图像的解码,我们引入了多尺度大核关注模块。该模块通过选择性地强调相关特征和细节,改进了分割过程,有助于更好地描绘物体。对自然和医学图像数据集的评估表明了我们的方法的效率和有效性。此外,所提出的方法的特点是其通用性和模型不可知性,允许与各种深度体系结构无缝集成。该代码可在\href{https://github.com/mindflow-institue/annotation_free_fewshot}{\textcolor{magenta}{GitHub}}上公开获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic classes, rendering them unsuitable for medical images due to the scarcity of annotations. To address this challenge, multiple contributions are proposed: First, inspired by spectral decomposition methods, the problem of image decomposition is reframed as a graph partitioning task. The eigenvectors of the Laplacian matrix, derived from the feature affinity matrix of self-supervised networks, are analyzed to estimate the distribution of the objects of interest from the support images. Secondly, we propose a novel self-supervised FSS framework that does not rely on any annotation. Instead, it adaptively estimates the query mask by leveraging the eigenvectors obtained from the support images. This approach eliminates the need for manual annotation, making it particularly suitable for medical images with limited annotated data. Thirdly, to further enhance the decoding of the query image based on the information provided by the support image, we introduce a multi-scale large kernel attention module. By selectively emphasizing relevant features and details, this module improves the segmentation process and contributes to better object delineation. Evaluations on both natural and medical image datasets demonstrate the efficiency and effectiveness of our method. Moreover, the proposed approach is characterized by its generality and model-agnostic nature, allowing for seamless integration with various deep architectures. The code is publicly available at \href{https://github.com/mindflow-institue/annotation_free_fewshot}{\textcolor{magenta}{GitHub}}.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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