arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.04531cs.CV
收藏

基于分解的遥感图像语义分割无监督域适应

Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);School of Information Science and Engineering, Wuhan University of Science and Technology(武汉科技大学信息科学与工程学院);School of Cyber Science and Engineering, Wuhan University(武汉大学网络空间安全学院);School of Electronic Engineering and Computer Science, Peking University(北京大学电子工程与计算机科学学院)

Xianping Ma, Xiaokang Zhang, Xingchen Ding, Man-On Pun, Siwei Ma

AI总结:

针对现有无监督域适应方法难以同时保留遥感图像语义分割中局部细节与全局语义的问题,提出基于多尺度高低频分解与全局-局部生成对抗网络的De-GLGAN框架,在多个基准上取得优于现有方法的效果。

摘要:

无监督域适应(UDA)技术对地球科学中的语义分割至关重要,可有效利用跨不同域的遥感图像。然而,现有大多数UDA方法聚焦于高层特征空间的域对齐,难以同时保留局部空间细节和全局上下文语义。为克服这些挑战,本文提出一种新颖的分解方案以指导域不变表征学习。具体而言,提出多尺度高低频分解(HLFD)模块,将特征图在不同子空间中分解为高频和低频分量。该分解被整合到全全局-局部生成对抗网络(GLGAN)中,该网络纳入全局-局部Transformer块(GLTB)以增强分解后特征的对齐。通过整合HLFD方案与GLGAN,开发出一种名为De-GLGAN的新型基于分解的UDA框架,以提升语义分割模型的跨域可迁移性和泛化能力。在两个UDA基准(即ISPRS Potsdam和Vaihingen,以及LoveDA Rural和Urban)上开展的大量实验表明,所提方法相较于现有最先进的UDA方法具有有效性和优越性。本工作的源代码可在https://github.com/sstary/SSRS获取。

英文摘要:

Unsupervised domain adaptation (UDA) techniques are vital for semantic segmentation in geosciences, effectively utilizing remote sensing imagery across diverse domains. However, most existing UDA methods, which focus on domain alignment at the high-level feature space, struggle to simultaneously retain local spatial details and global contextual semantics. To overcome these challenges, a novel decomposition scheme is proposed to guide domain-invariant representation learning. Specifically, multiscale high/low-frequency decomposition (HLFD) modules are proposed to decompose feature maps into high- and low-frequency components across different subspaces. This decomposition is integrated into a fully global-local generative adversarial network (GLGAN) that incorporates global-local transformer blocks (GLTBs) to enhance the alignment of decomposed features. By integrating the HLFD scheme and the GLGAN, a novel decomposition-based UDA framework called De-GLGAN is developed to improve the cross-domain transferability and generalization capability of semantic segmentation models. Extensive experiments on two UDA benchmarks, namely ISPRS Potsdam and Vaihingen, and LoveDA Rural and Urban, demonstrate the effectiveness and superiority of the proposed approach over existing state-of-the-art UDA methods. The source code for this work is accessible at https://github.com/sstary/SSRS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑