Papers › DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for...

DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks

23 Sep 2024IEEE Transactions on Geoscience and Remote Sensing 2024 9archive 2025-07-28

Wei Lu, Si-Bao Chen, Qing-Ling Shu, Jin Tang, and Bin Luo

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. However, 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.

PaperPDFCode

Code

lwCVer/DecoupleNet mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ARCComputational EfficiencyImage ClassificationObjectObject Detection In Aerial ImagesOriented Object DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification RESISC45 DecoupleNet D2 Top 1 Accuracy 95.87 #3 of 20 Archive leaderboard report
Object Detection In Aerial Images DIOR-R DecoupleNet D2 mAP 67.08 #9 of 9 Archive leaderboard report
Object Detection In Aerial Images DOTA DecoupleNet D2 mAP 78.04% #29 of 58 Archive leaderboard report
Semantic Segmentation LoveDA DecoupleNet D2 Category mIoU 53.1 #13 of 19 Archive leaderboard report
Semantic Segmentation UAVid DecoupleNet D2 Mean IoU 65.8 #9 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections