Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Anurag Kaushish, Ayan Sar, Sampurna Roy, Sudeshna Chakraborty, Prashant Trivedi, Tanupriya Choudhury, Kanav Gupta

TL;DR

This work tackles few-shot remote sensing classification under data scarcity, domain shifts, and multi-scale object appearances. It introduces AMC-MetaNet, a lightweight framework that uses a four-level feature pyramid guided by cross-scale correlations, an adaptive channel correlation module, and correlation-guided meta-learning, trained from scratch with approximately 600,000 parameters. On four RS datasets, it achieves up to 86.65% accuracy in 5-way 5-shot tasks and consistently outperforms baselines while being roughly 20x more parameter-efficient and capable of under 50 ms per-image inference. The approach offers a practical, scale-aware solution for real-world RS FSL and broadens the potential of lightweight models in geo-spatial image understanding.

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.

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

TL;DR

This work tackles few-shot remote sensing classification under data scarcity, domain shifts, and multi-scale object appearances. It introduces AMC-MetaNet, a lightweight framework that uses a four-level feature pyramid guided by cross-scale correlations, an adaptive channel correlation module, and correlation-guided meta-learning, trained from scratch with approximately 600,000 parameters. On four RS datasets, it achieves up to 86.65% accuracy in 5-way 5-shot tasks and consistently outperforms baselines while being roughly 20x more parameter-efficient and capable of under 50 ms per-image inference. The approach offers a practical, scale-aware solution for real-world RS FSL and broadens the potential of lightweight models in geo-spatial image understanding.

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 parameters, offering fewer parameters than ResNet-18 while maintaining high efficiency (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.
Paper Structure (10 sections, 9 equations, 2 figures, 2 tables)

This paper contains 10 sections, 9 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Problem Formulation
  4. Overall Architecture of AMC-MetaNet
  5. Adaptive Channel Correlation Module (ACCM)
  6. Meta-Learning Adaptation Module
  7. Experiments
  8. Comparison with Other Methods
  9. Ablation Study
  10. Conclusion

Figures (2)

  • Figure 1: Examples illustrating key challenges in remote sensing (RS) image classification: (Row 1) (Left) NWPU dataset showing an airplane from a wider view (a) and a zoomed view (b), highlighting the multi-scale challenge; (Row 1) (Right) EuroSAT (a) and AID (b) datasets showing the "forest" class, demonstrating domain shift where models trained on one dataset may fail to classify visually different instances from another; (Row 2) AID dataset with a soccer field labeled as "playground" (a) and another playground with a running track (b), showing the difficulty of generalizing from limited samples to visually distinct instances of the same class.
  • Figure 2: Architecture of the proposed AMC-MetaNet.