Few-shot learning in remote sensing remains challenging due to three factors: the scarcity of labeled data, substantial domain shifts, and the multi-scale nature of geospatial objects. To address these issues, we introduce Adaptive Multi-Scale Correlation Meta-Network (AMC-MetaNet), a lightweight yet powerful framework with three key innovations: (i) correlation-guided feature pyramids for capturing scale-invariant patterns, (ii) an adaptive channel correlation module (ACCM) for learning dynamic cross-scale relationships, and (iii) correlation-guided meta-learning that leverages correlation patterns instead of conventional prototype averaging. Unlike prior approaches that rely on heavy pre-trained models or transformers, AMC-MetaNet is trained from scratch with only ∼600K parameters, offering 20× fewer parameters than ResNet-18 while maintaining high efficiency (<50ms per image inference). AMC-MetaNet achieves up to 86.65\% accuracy in 5-way 5-shot classification on various remote sensing datasets, including EuroSAT, NWPU-RESISC45, UC Merced Land Use, and AID. Our results establish AMC-MetaNet as a computationally efficient, scale-aware framework for real-world few-shot remote sensing.
@article{arxiv.2601.12308,
title = {Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification},
author = {Anurag Kaushish and Ayan Sar and Sampurna Roy and Sudeshna Chakraborty and Prashant Trivedi and Tanupriya Choudhury and Kanav Gupta},
journal= {arXiv preprint arXiv:2601.12308},
year = {2026}
}