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
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI