Global Spectral Filter Memory Network for Video Object Segmentation

Yong Liu, R. Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang
{"title":"Global Spectral Filter Memory Network for Video Object Segmentation","authors":"Yong Liu, R. Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang","doi":"10.48550/arXiv.2210.05567","DOIUrl":null,"url":null,"abstract":"This paper studies semi-supervised video object segmentation through boosting intra-frame interaction. Recent memory network-based methods focus on exploiting inter-frame temporal reference while paying little attention to intra-frame spatial dependency. Specifically, these segmentation model tends to be susceptible to interference from unrelated nontarget objects in a certain frame. To this end, we propose Global Spectral Filter Memory network (GSFM), which improves intra-frame interaction through learning long-term spatial dependencies in the spectral domain. The key components of GSFM is 2D (inverse) discrete Fourier transform for spatial information mixing. Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head). We attribute this to semantic information extracting role for encoder and fine-grained details highlighting role for decoder. Thus, Low (High) Frequency Module is proposed to fit this circumstance. Extensive experiments on the popular DAVIS and YouTube-VOS benchmarks demonstrate that GSFM noticeably outperforms the baseline method and achieves state-of-the-art performance. Besides, extensive analysis shows that the proposed modules are reasonable and of great generalization ability. Our source code is available at https://github.com/workforai/GSFM.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":"103 1","pages":"648-665"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2210.05567","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 17

Abstract

This paper studies semi-supervised video object segmentation through boosting intra-frame interaction. Recent memory network-based methods focus on exploiting inter-frame temporal reference while paying little attention to intra-frame spatial dependency. Specifically, these segmentation model tends to be susceptible to interference from unrelated nontarget objects in a certain frame. To this end, we propose Global Spectral Filter Memory network (GSFM), which improves intra-frame interaction through learning long-term spatial dependencies in the spectral domain. The key components of GSFM is 2D (inverse) discrete Fourier transform for spatial information mixing. Besides, we empirically find low frequency feature should be enhanced in encoder (backbone) while high frequency for decoder (segmentation head). We attribute this to semantic information extracting role for encoder and fine-grained details highlighting role for decoder. Thus, Low (High) Frequency Module is proposed to fit this circumstance. Extensive experiments on the popular DAVIS and YouTube-VOS benchmarks demonstrate that GSFM noticeably outperforms the baseline method and achieves state-of-the-art performance. Besides, extensive analysis shows that the proposed modules are reasonable and of great generalization ability. Our source code is available at https://github.com/workforai/GSFM.
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
用于视频目标分割的全局频谱滤波记忆网络
本文通过增强帧内交互来研究半监督视频目标分割。目前基于记忆网络的方法主要关注帧间的时间参考,而很少关注帧内的空间依赖。具体来说,这些分割模型容易受到某一帧内不相关的非目标物体的干扰。为此,我们提出了全局频谱滤波记忆网络(GSFM),该网络通过学习频谱域的长期空间依赖关系来改善帧内交互。GSFM的关键部分是用于空间信息混合的二维(逆)离散傅里叶变换。此外,我们还通过经验发现,在编码器(主干)中需要增强低频特征,而在解码器(分割头)中需要增强高频特征。我们将其归因于编码器的语义信息提取作用和解码器的细粒度细节突出作用。因此,提出了低(高)频率模块来适应这种情况。在流行的DAVIS和YouTube-VOS基准测试上进行的大量实验表明,GSFM明显优于基线方法,并实现了最先进的性能。此外,广泛的分析表明,所提出的模块是合理的,具有很强的泛化能力。我们的源代码可从https://github.com/workforai/GSFM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。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding Rethinking Confidence Calibration for Failure Prediction PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry Diverse Human Motion Prediction Guided by Multi-level Spatial-Temporal Anchors
×
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