LiteLKG-Net: A Lightweight Network With Multiscale Large Kernel Attention and Gated Spatial Feature Fusion for Remote Sensing Change Detection
IEEE Transactions on Geoscience and Remote Sensing · 2026 · 64 · 5621118-5621118
DOI: 10.1109/tgrs.2026.3690664 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2026. Verfasst von Zhihua Hua und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 70 Literaturangaben.
Abstract (Originalsprache)
With the advancement of Earth observation technology, remote sensing change detection (RSCD) has become an effective means to monitor dynamic changes in surface objects, widely applied in urban planning, environmental disaster monitoring, and other fields. Although Transformer-based methods exhibit strong global modeling capabilities, they often suffer from high computational complexity and excessive parameter counts, while traditional convolutional neural network (CNN)-based methods are constrained by limited convolutional kernel sizes, leading to the neglect of global contextual information. These limitations hinder their applicability in resource-constrained and complex scenarios. To address these challenges, this article proposes a LiteLKG-Net, which integrates multiscale large kernel attention (MLKA) and a gating mechanism to maintain high detection performance while significantly reducing computational costs. First, we design a multiscale attention module (MAM) composed of an MLKA and a gated spatial attention unit (GSAU). The MLKA aggregates global and local information to capture rich change features at varying granularities, while the GSAU combines the gating mechanism with spatial attention to fully exploit contextual spatial information with reduced computational overhead. Second, we construct a channel interaction module (CIM) to enhance cross-temporal feature interaction, thereby improving spatiotemporal semantic perception. A feature fusion module (FFM) is further introduced to aggregate multiscale features, enhancing the model’s capability to discern fine-grained details. The decoder incorporates a multilevel residual fusion strategy and embeds a gated mechanism module (GMM) to adaptively filter critical features, significantly enhancing model accuracy and robustness. Finally, we adopt MobileNetV2 as the Siamese encoder to efficiently extract features while minimizing computational complexity. Comprehensive experiments are conducted on three benchmark datasets. Both visual and quantitative results demonstrate that our proposed LiteLKG-Net outperforms ten other state-of-the-art networks. In addition, ablation studies validate the effectiveness of each proposed module.
Zitieren
APA
Hua, Z., Zhang, L., Cai, Y., & Wen, K. (2026). LiteLKG-Net: A Lightweight Network With Multiscale Large Kernel Attention and Gated Spatial Feature Fusion for Remote Sensing Change Detection. IEEE Transactions on Geoscience and Remote Sensing, 64, 5621118-5621118. https://doi.org/10.1109/tgrs.2026.3690664
Vancouver
Hua Z, Zhang L, Cai Y, Wen K. LiteLKG-Net: A Lightweight Network With Multiscale Large Kernel Attention and Gated Spatial Feature Fusion for Remote Sensing Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 2026;64:5621118-5621118. doi:10.1109/tgrs.2026.3690664
BibTeX
@article{Hua2026,
author = {Hua, Zhihua and Zhang, Longfei and Cai, Yijian and Wen, Kui},
title = {LiteLKG-Net: A Lightweight Network With Multiscale Large Kernel Attention and Gated Spatial Feature Fusion for Remote Sensing Change Detection},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2026},
volume = {64},
pages = {5621118--5621118},
doi = {10.1109/tgrs.2026.3690664}
}
EUVIMED