Oct 2026· PLoS ONE· Vol 21· 0 citations· 46 references
Medicine
TL;DR
GFLNet, a lightweight single-stage detector, which is based on collaborative feature modeling and knowledge-guided compression, is proposed, designed to achieve efficient spatial-channel interaction while reducing computational cost.
Abstract
Remote sensing images usually exhibits densely distributed targets and scale disparities. In such scenarios, it is still challenging to preserve high detection precision while controlling costs and inference latency. To address this issue, we propose GFLNet, a lightweight single-stage detector, which is based on collaborative feature modeling and knowledge-guided compression. Specifically, Ghost-Shuffle dual fusion convolution (GSD-Fuse) is designed to achieve efficient spatial-channel interaction while reducing computational cost; an adaptive receptive-field selection module inspired by LSKNet is introduced into the deeper backbone and neck stages to adaptively adjust contextual responses for small-object and multi-scale detection; finally, LB-Compress combines layer-adaptive magnitude pruning with Bidirectional Cross-task Knowledge Distillation (BCKD) to form a compact network suitable for practical deployment. Evaluated on the DIOR and UCAS-AOD datasets, GFLNet improves mAP@0.5 over the baseline by 3.9% and 3.4%, respectively. Moreover, the model contains only 2.35M parameters, with a calculation of 5.6 GFLOPs, and an inference speed of 261 FPS on the GPU, thereby delivering a favorable accuracy-efficiency synergy.
Lightweight single-image super-resolution (SISR) requires effective local structural representation and broader contextual modeling under a restricted computational budget. We propose DPALSR, a Dual Prior-Aware Lightweight Super-Resolution Network that conditions successive attention-query representations with compleme...
Wen-Jie Wang, Hui-Ying Xu, Han-Jiang Lin et al.· Algorithms· 0 citations
The rapid growth of remote sensing images brings significant challenges to bandwidth and onboard storage resources. This makes remote sensing image compression essential for large-scale storage and subsequent processing. However, achieving a balance between reconstruction quality and model complexity remains a challeng...
Yu-Jie Song, Dong-Yang Liu, Xue-Jian Liang et al.· IEEE Geoscience and Remote S...· 0 citations
Small targets in UAV images remain difficult to detect because practical deployment requires both reliable localization and low computational burden. Most lightweight detectors reduce cost mainly through backbone compression, while the transmission operators inside the feature pyramid are less frequently optimized. To...
Yan-Shan Zhang, Wan Li, Yuan-Zhang Fan et al.· International Conference on...· 0 citations
While content-adaptive schemes have delivered notable advances in image super-resolution (SR), existing approaches typically focus on texture complexity and ignore intrinsic degradation factors (e.g., blur kernels or noise patterns), leading to suboptimal computation allocation and reconstruction performance. To remedy...
Song-Li Wu, Hao-Nan Jiang, Ji-Xuan Fan et al.· arXiv.org· 0 citations
Real-time object detection under low illumination remains challenging because weak contrast, sensor noise, and feature degradation can reduce target discriminability, while practical deployment also requires careful control of model complexity and computational cost. Existing enhancement-then-detect pipelines can impro...
Min Hao, Zhe Chen, Ji-Long Li et al.· IEEE Access· 0 citations
Remote sensing change detection (CD) supports urban expansion, disaster assessment, and land-use monitoring. Transformer models are accurate, but quadratic attention and memory demand hinder near-sensor deployment. LCSF-Net is a lightweight Siamese CD network with a multi-level lightweight Cross-Scale Fusion (LCSF) des...
Bo-Hai Tang, Jian-Lin Na, Dan-Dan Gu et al.· 3rd International Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.