轻量级模型解决遥感图像少样本分类难题，兼顾多尺度与快速推理。
Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification
- 通过相关性引导的特征金字塔捕捉尺度不变特征
- 仅60万参数实现86.65%准确率，单图推理<50ms
- 适合资源受限场景下的实时遥感分类应用
遥感图像少样本学习面临标签数据稀缺、域偏移显著及地物对象多尺度等挑战。为此，提出自适应多尺度相关性元网络（AMC-MetaNet），具三项创新：(i) 相关性引导的特征金字塔以捕获尺度不变模式；(ii) 自适应通道相关模块（ACCM）学习动态跨尺度关系；(iii) 基于相关性模式而非原型平均的元学习策略。相比依赖大型预训练模型或Transformer的方法，AMC-MetaNet从零训练，参数量仅约60万，为ResNet-18的1/20，且单图推理时间低于50毫秒。在EuroSAT、NWPU-RESISC45、UC Merced Land Use和AID等多个遥感数据集上，5类5样本分类最高达86.65%准确率。结果表明，该框架兼具计算高效与尺度感知能力，适用于真实世界少样本遥感场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。