GLUSE: Enhanced Channel-Wise Adaptive Gated Linear Units SE for Onboard Satellite Earth Observation Image Classification
Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Geoffrey Eappen, Prabhu Thiruvasagam, Hong-Fu Chou, Duc-Dung Tran, Hung Nguyen-Kha, Luis M. Garces-Socarras, Jorge L. Gonzalez-Rios, Juan Carlos Merlano-Duncan, Symeon Chatzinotas
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ltdung/snt-sentryOfficialIn papernone★ 8
Abstract
This study introduces ResNet-GLUSE, a lightweight ResNet variant enhanced with Gated Linear Unit-enhanced Squeeze-and-Excitation (GLUSE), an adaptive channel-wise attention mechanism. By integrating dynamic gating into the traditional SE framework, GLUSE improves feature recalibration while maintaining computational efficiency. Experiments on EuroSAT and PatternNet datasets confirm its effectiveness, achieving exceeding 94\% and 98\% accuracy, respectively. While MobileViT achieves 99\% accuracy, ResNet-GLUSE offers 33x fewer parameters, 27x fewer FLOPs, 33x smaller model size (MB), 6x lower power consumption (W), and 3x faster inference time (s), making it significantly more efficient for onboard satellite deployment. Furthermore, due to its simplicity, ResNet-GLUSE can be easily mimicked for neuromorphic computing, enabling ultra-low power inference at just 852.30 mW on Akida Brainchip. This balance between high accuracy and ultra-low resource consumption establishes ResNet-GLUSE as a practical solution for real-time Earth Observation (EO) tasks. Reproducible codes are available in our shared repository.