{"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/decouplenet-a-lightweight-backbone-network","title":"DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks","arxiv_id":null,"date":"2024-09-23","proceeding":"IEEE Transactions on Geoscience and Remote Sensing 2024 9","authors":["Wei Lu","Si-Bao Chen","Qing-Ling Shu","Jin Tang","and Bin Luo"],"abstract":"In the realm of computer vision (CV), balancing speed and accuracy remains a significant challenge. Recent efforts have focused on developing lightweight networks that optimize computational efficiency and feature extraction. How\u0002ever, in remote sensing (RS) imagery, where small and multiscale object detection is critical, these networks often fall short in performance. To address these challenges, DecoupleNet is proposed, an innovative lightweight backbone network specifically designed for RS visual tasks in resource-constrained environments. DecoupleNet incorporates two key modules: the feature integration downsampling (FID) module and the multibranch feature decoupling (MBFD) module. The FID module preserves small object features during downsampling, while the MBFD module enhances small and multiscale object feature representation through a novel decoupling approach. Comprehensive evaluations on three RS visual tasks demonstrate DecoupleNet’s superior balance of accuracy and computational efficiency compared to existing lightweight networks. On the NWPU-RESISC45 classification dataset, DecoupleNet achieves a top-1 accuracy of 95.30%, surpassing FasterNet by 2%, with fewer parameters and lower computational overhead. In object detection tasks using the DOTA 1.0 test set, DecoupleNet records an accuracy of 78.04%, outperforming ARC-R50 by 0.69%. For semantic segmentation on the LoveDA test set, DecoupleNet achieves 53.1% accuracy, surpassing UnetFormer by 0.70%. These findings open new avenues for advancing RS image analysis on resource-constrained devices, addressing a pivotal gap in the field. The code and pretrained models are publicly available at https://github.com/lwCVer/DecoupleNet.","url_abs":"https://ieeexplore.ieee.org/document/10685518","url_pdf":"https://ieeexplore.ieee.org/document/10685518","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":"decouplenet-a-lightweight-backbone-network","repo_url":"https://github.com/lwCVer/DecoupleNet","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection-in-aerial-images","task_name":"Object Detection In Aerial Images"},{"task_slug":"oriented-object-detection","task_name":"Oriented Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"DecoupleNet D2","rank_in_archive_order":3,"of":20,"metrics":{"Top 1 Accuracy":"95.87"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dior-r","task":"Object Detection In Aerial Images","dataset":"DIOR-R","model":"DecoupleNet D2","rank_in_archive_order":9,"of":9,"metrics":{"mAP":"67.08"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset":"DOTA","model":"DecoupleNet D2","rank_in_archive_order":29,"of":58,"metrics":{"mAP":"78.04%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-loveda","task":"Semantic Segmentation","dataset":"LoveDA","model":"DecoupleNet D2","rank_in_archive_order":13,"of":19,"metrics":{"Category mIoU":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-uavid","task":"Semantic Segmentation","dataset":"UAVid","model":"DecoupleNet D2","rank_in_archive_order":9,"of":10,"metrics":{"Mean IoU":"65.8"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}