CLANET: a cross-linear attention network for semantic segmentation of urban scenes remote sensing images

ABSTRACTSemantic segmentation of high-resolution remote sensing images is important in land cover classification, road extraction, building extraction, water extraction, etc. However, high-resolution remote-sensing images have a lot of details. Due to the fixed receptive field of convolution blocks, it is impossible to model the correlation of global features. In addition, complex fusion methods cannot integrate spatial and global context information. In order to solve these problems, this paper proposes a cross-linear attention network (CLANet) to capture spatial and context information in images. The structure consists of a spatial branch and a context branch. The spatial branch is constructed by stacked convolution to better capture spatial information. The context branch models the global information based on the transformer deformation module. In addition, to effectively fuse spatial and context information, this paper also designs a feature fusion module (FFM), which uses a cross-linear attention mechanism for feature aggregation. Finally, this paper conducts many experiments on the ISPRS Vaihingen and the ISPRS Potsdam datasets. Among them, 82.28% of mIoU achieves on the ISPRS Vaihingen dataset. The experimental results show that CLANet has better performance and effect than the methods in recent years.KEYWORDS: Remote sensingsemantic segmentationcross attentionconvolutional neural network AcknowledgementsWe would like to thank the Key Laboratory of Software Engineering, Xinjiang University for providing us with GPU computing resources. We would also like to thank the anonymous reviewers for their voluntary and constructive comments, which helped to improve this paper.Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis work is supported in part by the National Natural Science Foundation of China [62266043 and 61966035] and the National Defense Science and Technology Bureau’s high-resolution-to-ground observation system major project [95-Y50G37-9001-22/23].