计算机科学与探索2024，Vol.18Issue(8)：2091-2108,18.DOI:10.3778/j.issn.1673-9418.2307098
结合原型的两阶段遥感图像无监督域适应分割模型
Prototype-Combined Two-Stage Unsupervised Domain Adaptation Segmentation Model for Remote Sensing Images
摘要
Abstract
Remote sensing image data have a large volume and a wide range of land cover categories.There is a sig-nificant disparity between local and global features,and noticeable differences in the intra-domain features.This makes it challenging for traditional transfer learning to effectively improve the model's generalization performance.In light of this,based on the traditional unsupervised domain adaptation model that aligns features between do-mains,a prototype-combined two-stage unsupervised domain adaptation segmentation model for remote sensing images is proposed.Firstly,category features are represented using prototypes.The prototype acquisition module is introduced to obtain and update prototypes.By applying prototypes through the prototype imposition module in combination with self-attention,global category features are imposed on the locally cropped image features.This en-ables the segmentation network to consider both local and global category information,thus better extracting invari-ant features from both domains.Secondly,the target domain images are divided into easy and hard segments using pseudo-labels.Through adversarial and self-training methods,the intra-domain feature differences in the target do-main are reduced,facilitating better extraction of intra-domain invariant features from easy and hard target domain images.Lastly,the segmentation prediction maps,which contain known pixel categories,are used to compute the contextual relationships between each pixel and its neighboring pixels.A pixel context relationship graph is generated to determine the domain from which the pixel context relationship in the output-level discriminative network origi-nates.This compels the segmentation network to better extract domain-invariant contextual relationships and allevi-ate the problem of spectral confusion.Experimental results on two datasets demonstrate that the proposed model effec-tively mitigates the challenges posed by large disparities between local and global features,significant intra-domain feature differences,and the issue of spectral confusion,leading to a decline in model transfer performance.Com-pared with advanced domain adaptation segmentation methods,the proposed model exhibits superior performance.关键词
图像分割/遥感图像/无监督域适应/全局和局部特征/像素上下文关系Key words
image segmentation/remote sensing images/unsupervised domain adaptation/global and local fea-tures/pixel contextual relationship分类
信息技术与安全科学引用本文复制引用
李政威,汪西莉,艾美..结合原型的两阶段遥感图像无监督域适应分割模型[J].计算机科学与探索,2024,18(8):2091-2108,18.基金项目
科技部青藏高原科考专项第二次青藏高原综合科学考察研究项目(2019QZKK0405). This work was supported by the Second Tibetan Plateau Scientific Expedition and Research Program(2019QZKK0405). （2019QZKK0405）
