A Prototype-Aware Learning and Dual-View Regularization Network for Weakly Supervised Change Detection in VHR Remote Sensing Images

计算机科学 变更检测 判别式 稳健性(进化) 人工智能 正规化(语言学) 模式识别(心理学) 目标检测 机器学习 遥感 遥感应用 概率逻辑 上下文图像分类 任务分析 数据挖掘 注释 标记数据 深度学习 杂乱 数据建模 噪声数据 噪音(视频) 噪声测量 分拆(数论) 高光谱成像
作者
Yongqi Chen,Shou Feng,Chunhui Zhao,Yingjie Tang,Wei Li,Ran Tao
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:63: 1-15 被引量:13
标识
DOI:10.1109/tgrs.2025.3608817
摘要

Change detection (CD) is a critical task for monitoring the spatiotemporal evolution of the Earth’s surface. Recently, due to the advantages of reduced annotation cost and improved labeling efficiency, weakly supervised change detection (WSCD) has attracted increasing attention. However, existing WSCD methods encounter several critical challenges, including incomplete activation of class activation maps (CAMs), interference from noisy pseudo-labels during training, and instability in change recognition caused by illumination and environmental variations. To address these issues, we propose a prototype-aware learning and dual-view regularization network (PDRNet) for image-level WSCD. Specifically, to address the issue of incomplete activation caused by the tendency of CAM to focus excessively on locally discriminative regions, PDRNet devises a prototype-aware module (PAM), which captures stable category prototypes and refines CAM quality by reactivating hierarchical features. Furthermore, to mitigate the network’s sensitivity to noisy pseudo-labels, a dual-view regularization strategy (DRS) is designed to partition pseudo-labels into clean and noisy regions. Region-specific regularization is subsequently employed to improve the robustness of the model against noisy supervision. Finally, to enhance the capability of identifying changed regions, PDRNet constructs a wavelet-based change enhancement module (WCEM) to decompose bi-temporal features into multiple frequency bands. This facilitates the comprehensive utilization of low-frequency structural semantics and high-frequency texture details. Extensive experiments and analyses conducted on three publicly available CD datasets yield the superiority of PDRNet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
chenjunhuan发布了新的文献求助10
刚刚
1秒前
molihuakai的应助被谨慎的秋烟采纳,获得10
2秒前
盈虚者发布了新的文献求助10
3秒前
theverve发布了新的文献求助10
3秒前
4秒前
小蘑菇的应助被铁头霸霸采纳,获得10
5秒前
zhangzhangZZZ完成签到,获得积分10
5秒前
6秒前
科目三的应助被ZRJ采纳,获得10
6秒前
Cc完成签到 ,获得积分10
7秒前
orixero的应助被眼睛大的书易采纳,获得10
7秒前
7秒前
泪西瓜完成签到,获得积分10
8秒前
Ava的应助被缪甲烷采纳,获得10
8秒前
丫丫完成签到 ,获得积分10
8秒前
9秒前
温温完成签到 ,获得积分10
9秒前
9秒前
10秒前
wuwui完成签到 ,获得积分10
11秒前
林阙发布了新的文献求助10
13秒前
13秒前
Zz发布了新的文献求助10
13秒前
上官若男的应助被苹果思天采纳,获得10
13秒前
Ethereal发布了新的文献求助10
13秒前
14秒前
15秒前
16秒前
16秒前
16秒前
Jasper的应助被benhzh采纳,获得10
17秒前
菜不透完成签到,获得积分10
17秒前
蓝月发布了新的文献求助10
19秒前
JIMS发布了新的文献求助10
19秒前
柠檬不萌完成签到 ,获得积分10
20秒前
20秒前
20秒前
Lucas的应助被科研通管家采纳,获得20
22秒前
22秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8158056
求助须知:如何正确求助?哪些是违规求助? 9553944
关于积分的说明 21716733
捐赠科研通 7747388
什么是DOI,文献DOI怎么找? 3426934
关于科研通互助平台的介绍 2551676
邀请新用户注册赠送积分活动 2471038