EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

LACE-Net: A Swin Transformer with Local Frequency-Domain Energy and Adaptive Contrast Enhancement for Fine-Grained Land Cover Classification

Yongmei Tan, Gong Chen, Yan Huang, Hengzhou Ye, Jincheng Tang

Computers · 2026-04-28 · 15 (5) · 281

DOI: 10.3390/computers15050281 ↗

At a glance

Journal article in Computers, published online on 2026-04-28. Written by Yongmei Tan and 4 co-authors. 34 references. The full text is freely available (open access, CC BY 4.0). Funded by: Technical Services for Intelligent Identification of Land Categories in Guangxi, National Natural Science Foundation of China, Guangxi Major S&T Special Program.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The Swin Transformer exhibits limitations in fine-grained land use and land cover (LULC) classification, particularly in capturing high-frequency texture details and representing low-contrast regions. To address these issues, we propose a novel network model, termed LACE-Net, which integrates local frequency-domain energy and adaptive contrast enhancement. Built upon the Swin Transformer backbone, the model introduces an innovative Local Frequency-Domain Energy-Adaptive Contrast Enhancement Multi-Scale Attention (LACE). This block consists of parallel branches for frequency-domain perception and contrast enhancement, which effectively combine texture and illumination physical priors. In addition, a texture-adaptive momentum adjustment mechanism is incorporated to refine the spatial enhancement attention weights dynamically. Consequently, LACE-Net greatly strengthens the modeling and representation of high-frequency details and complex spatial structural features. Experiments are performed on a self-constructed Guangxi regional dataset (denoted as GLC-30) and the publicly available remote sensing scene classification benchmark dataset NWPU-RESISC45. The results show that LACE-Net achieves a Top-1 accuracy (Top-1 Acc) of 96.48% and a macro-averaged F1 score (mF1) of 93.13%. These results outperform current mainstream vision models, particularly in mitigating the spectral confusion issue of “same spectrum, different objects.” The model exhibits superior fine-grained classification performance and robust generalization across datasets.

Funding

  • Technical Services for Intelligent Identification of Land Categories in Guangxi
  • National Natural Science Foundation of China
  • Guangxi Major S&T Special Program

Cite

APA

Tan, Y., Chen, G., Huang, Y., Ye, H., & Tang, J. (2026). LACE-Net: A Swin Transformer with Local Frequency-Domain Energy and Adaptive Contrast Enhancement for Fine-Grained Land Cover Classification. Computers, 15(5), 281. https://doi.org/10.3390/computers15050281

Vancouver

Tan Y, Chen G, Huang Y, Ye H, Tang J. LACE-Net: A Swin Transformer with Local Frequency-Domain Energy and Adaptive Contrast Enhancement for Fine-Grained Land Cover Classification. Computers. 2026;15(5):281. doi:10.3390/computers15050281

BibTeX
@article{Tan2026,
  author = {Tan, Yongmei and Chen, Gong and Huang, Yan and Ye, Hengzhou and Tang, Jincheng},
  title = {LACE-Net: A Swin Transformer with Local Frequency-Domain Energy and Adaptive Contrast Enhancement for Fine-Grained Land Cover Classification},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {281},
  doi = {10.3390/computers15050281}
}
Start for free →