English

Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery

Computer Vision and Pattern Recognition 2025-07-16 v1

Abstract

We present GLOD, a transformer-first architecture for object detection in high-resolution satellite imagery. GLOD replaces CNN backbones with a Swin Transformer for end-to-end feature extraction, combined with novel UpConvMixer blocks for robust upsampling and Fusion Blocks for multi-scale feature integration. Our approach achieves 32.95\% on xView, outperforming SOTA methods by 11.46\%. Key innovations include asymmetric fusion with CBAM attention and a multi-path head design capturing objects across scales. The architecture is optimized for satellite imagery challenges, leveraging spatial priors while maintaining computational efficiency.

Keywords

Cite

@article{arxiv.2507.11040,
  title  = {Combining Transformers and CNNs for Efficient Object Detection in High-Resolution Satellite Imagery},
  author = {Nicolas Drapier and Aladine Chetouani and Aurélien Chateigner},
  journal= {arXiv preprint arXiv:2507.11040},
  year   = {2025}
}

Comments

11 pages, 9 figures

R2 v1 2026-07-01T04:01:48.494Z