Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification

2026-01-18

AI Summary

This study addresses the challenges of few-shot classification in remote sensing imagery, including scarce annotations, domain shift, and multi-scale land cover variations. To this end, the authors propose a lightweight framework that innovatively integrates a correlation-guided feature pyramid with an Adaptive Channel Correlation Module (ACCM). Departing from conventional prototype averaging, the method employs correlation-based patterns within a meta-learning paradigm, substantially reducing model complexity. Evaluated on benchmark remote sensing datasets such as EuroSAT, the approach achieves a 5-way 5-shot classification accuracy of 86.65% with only approximately 600,000 parameters—roughly one-twentieth the size of ResNet-18—and requires less than 50 milliseconds for single-image inference.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

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 $\sim600K$ parameters, offering $20\times$ fewer parameters than ResNet-18 while maintaining high efficiency ($<50$ms 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.

Problem

• few-shot learning
• remote sensing
• multi-scale
• domain shift
• data scarcity

Innovation

• few-shot learning
• multi-scale correlation
• meta-learning
• remote sensing image classification
• lightweight neural network