English

Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing

Computer Vision and Pattern Recognition 2026-04-03 v1 Artificial Intelligence Image and Video Processing

Abstract

Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images. This paper revisits the classical multi-scale representation learning problem but under the general framework of self-supervised learning for remote sensing image understanding. We present Cross-Scale MAE, a self-supervised model built upon the Masked Auto-Encoder (MAE).During pre-training, Cross-Scale MAE employs scale augmentation techniques and enforces cross-scale consistency constraints through both contrastive and generative losses to ensure consistent and meaningful representations well-suited for a wide range of downstream tasks. Further, our implementation leverages the xFormers library to accelerate network pre-training on a single GPU while maintaining the quality of learned representations. Experimental evaluations demonstrate that Cross-Scale MAE exhibits superior performance compared to standard MAE and other state-of-the-art remote sensing MAE methods.

Keywords

Cite

@article{arxiv.2401.15855,
  title  = {Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing},
  author = {Maofeng Tang and Andrei Cozma and Konstantinos Georgiou and Hairong Qi},
  journal= {arXiv preprint arXiv:2401.15855},
  year   = {2026}
}
R2 v1 2026-06-28T14:29:40.790Z