{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sfa-net-semantic-feature-adjustment-network","title":"SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation","arxiv_id":null,"date":"2024-09-03","proceeding":"Remote Sensing 2024 9","authors":["Gyutae Hwang","Jiwoo Jeong","Sang Jun Lee"],"abstract":"Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M.","url_abs":"https://www.mdpi.com/2072-4292/16/17/3278","url_pdf":"https://www.mdpi.com/2072-4292/16/17/3278/pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sfa-net-semantic-feature-adjustment-network","repo_url":"https://github.com/j2jeong/priv","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"land-cover-classification","task_name":"Land Cover Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-fine-grained-cloud","task":"Semantic Segmentation","dataset":"Fine-Grained Cloud Segmentation Dataset","model":"SFA-Net","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"74.88"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-fine-grained-grass","task":"Semantic Segmentation","dataset":"Fine-Grained Grass Segmentation Dataset","model":"SFA-Net","rank_in_archive_order":2,"of":10,"metrics":{"mIoU":"51.21"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-isprs-potsdam","task":"Semantic Segmentation","dataset":"ISPRS Potsdam","model":"SFA-Net","rank_in_archive_order":19,"of":20,"metrics":{"Mean F1":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-isprs-vaihingen","task":"Semantic Segmentation","dataset":"ISPRS Vaihingen","model":"SFA-Net","rank_in_archive_order":12,"of":12,"metrics":{"Average F1":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-loveda","task":"Semantic Segmentation","dataset":"LoveDA","model":"SFA-Net","rank_in_archive_order":3,"of":19,"metrics":{"Category mIoU":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-uavid","task":"Semantic Segmentation","dataset":"UAVid","model":"SFA-Net","rank_in_archive_order":4,"of":10,"metrics":{"Mean IoU":"70.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}