TCNet: Temporal Consistency Network for Semisupervised Change Detection

Qidi Shu, Jiarui Hu, Jun Pan, Yuchuan Bai, Zhuoer Zhang, Zongrui Li
{"title":"TCNet: Temporal Consistency Network for Semisupervised Change Detection","authors":"Qidi Shu, Jiarui Hu, Jun Pan, Yuchuan Bai, Zhuoer Zhang, Zongrui Li","doi":"10.1109/AICIT55386.2022.9930313","DOIUrl":null,"url":null,"abstract":"Change detection is a challenging task in earth observation. In recent years, deep learning techniques have been widely applied in change detection and achieved impressive progress. However, deep learning based change detection methods heavily rely on a large amount of annotated samples. Labeling for change detection is a time-consuming and labor-intensive task. In order to solve this problem, we propose a novel temporal consistency network (TCNet) for semisupervised change detection. Motivated by the fact that different input sequences have no effect on the prediction results of change detection, our method learns the distribution of unlabeled data by enforce the consistency of the prediction obtained with different input sequences. Specifically, for labeled samples, two segmentation networks with the same structure are trained with two different input sequences. For the unlabeled samples, we perform the forward prediction on the two segmentation networks with corresponding input sequence to obtain two results of change detection. Then, the supervised signals can be generated by minimizing the difference between two predicted results. In this way, the distribution of unlabeled data can be fully explored thus enhancing the generalization of change detection. Experiments on google dataset show the effectiveness of the proposed method.","PeriodicalId":231070,"journal":{"name":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICIT55386.2022.9930313","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Change detection is a challenging task in earth observation. In recent years, deep learning techniques have been widely applied in change detection and achieved impressive progress. However, deep learning based change detection methods heavily rely on a large amount of annotated samples. Labeling for change detection is a time-consuming and labor-intensive task. In order to solve this problem, we propose a novel temporal consistency network (TCNet) for semisupervised change detection. Motivated by the fact that different input sequences have no effect on the prediction results of change detection, our method learns the distribution of unlabeled data by enforce the consistency of the prediction obtained with different input sequences. Specifically, for labeled samples, two segmentation networks with the same structure are trained with two different input sequences. For the unlabeled samples, we perform the forward prediction on the two segmentation networks with corresponding input sequence to obtain two results of change detection. Then, the supervised signals can be generated by minimizing the difference between two predicted results. In this way, the distribution of unlabeled data can be fully explored thus enhancing the generalization of change detection. Experiments on google dataset show the effectiveness of the proposed method.
半监督变化检测的时间一致性网络
变化探测是对地观测中一项具有挑战性的任务。近年来,深度学习技术在变化检测中得到了广泛的应用,并取得了令人瞩目的进展。然而,基于深度学习的变化检测方法严重依赖于大量带注释的样本。为变更检测标记是一项耗时且费力的任务。为了解决这个问题,我们提出了一种新的时间一致性网络(TCNet)用于半监督变化检测。基于不同的输入序列对变化检测的预测结果没有影响的事实,我们的方法通过增强不同输入序列预测结果的一致性来学习未标记数据的分布。具体来说,对于标记的样本,用两个不同的输入序列训练两个具有相同结构的分割网络。对于未标记的样本,我们对两个具有相应输入序列的分割网络进行前向预测,得到两个变化检测结果。然后,通过最小化两个预测结果之间的差异来生成监督信号。这样可以充分挖掘未标记数据的分布,从而增强变化检测的泛化能力。在google数据集上的实验证明了该方法的有效性。
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
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