面向类感知和类不可知的少镜头分割对齐联合框架

Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Fei Wang, Peng Chen
{"title":"面向类感知和类不可知的少镜头分割对齐联合框架","authors":"Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Fei Wang, Peng Chen","doi":"10.48550/arXiv.2211.01310","DOIUrl":null,"url":null,"abstract":"Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.","PeriodicalId":87238,"journal":{"name":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation\",\"authors\":\"Kai Huang, Mingfei Cheng, Yang Wang, Bochen Wang, Ye Xi, Fei Wang, Peng Chen\",\"doi\":\"10.48550/arXiv.2211.01310\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.\",\"PeriodicalId\":87238,\"journal\":{\"name\":\"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2211.01310\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer vision - ACCV ... : ... Asian Conference on Computer Vision : proceedings. Asian Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2211.01310","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

少镜头分割(FSS)的目的是在只给定少量注释的支持图像的情况下,分割不可见类的对象。大多数现有的方法都是简单地将查询特征与独立的支持原型拼接在一起,然后将混合特征馈送给解码器对查询图像进行分割。虽然已经取得了很大的进步,但是由于类的变化和背景的混淆,现有的方法仍然面临着类偏差。在本文中,我们提出了一个联合框架,它结合了更有价值的类感知和类不可知的对齐指导来促进分割。具体来说,我们设计了一个混合对齐模块,该模块建立了多尺度查询支持对应关系,从相应的支持特征中挖掘每个查询图像最相关的类感知信息。此外,我们探索利用基类知识来生成与类无关的先验掩码,该掩码通过突出显示所有对象区域,特别是那些看不见的类,来区分真实背景和前景。通过类感知和类不可知对齐引导的联合聚合,可以获得更好的查询图像分割性能。在PASCAL-$5^i$和COCO-$20^i$数据集上的大量实验表明,我们提出的联合框架性能更好,特别是在单镜头设置上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation
Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.
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
期刊最新文献
MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning NoiseTransfer: Image Noise Generation with Contrastive Embeddings Layout-guided Indoor Panorama Inpainting with Plane-aware Normalization Layered-Garment Net: Generating Multiple Implicit Garment Layers from a Single Image RDRN: Recursively Defined Residual Network for Image Super-Resolution
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1