轻量级卷积混合网络提升遥感图像分类精度与效率
SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification
- 采用多尺度深度卷积与点卷积交替设计，兼顾局部与上下文特征提取
- 在AID和EuroSAT上分别达74.7%和93.9%准确率，参数量与计算量更低
- 适合资源受限场景下的遥感图像分类任务，尤其对小样本数据表现良好
遥感场景分类在地球观测中至关重要，可自动识别航空与卫星影像中的土地利用与土地覆盖（LULC）模式。尽管卷积神经网络（CNN）和视觉变压器（ViT）取得进展，但因空间分辨率、视角、方向及背景差异，模型泛化能力仍受挑战。本文提出一种基于卷积混合器范式的轻量级架构，通过多尺度深度卷积实现空间混合，结合点卷积进行通道混合，高效提取局部与上下文信息，同时保持低参数量与计算量。在AID和EuroSAT基准测试中，模型在AID上达到74.7%总体准确率、74.57%平均准确率与73.79%Kappa值，在EuroSAT上分别为93.90%、93.93%和93.22%。结果表明，该方法在精度与效率间取得良好平衡，优于主流的CNN与变压器模型。代码将公开于：https://github.com/mqalkhatib/SceneMixer
原文摘要 · Abstract (English)
Remote sensing scene classification plays a key role in Earth observation by enabling the automatic identification of land use and land cover (LULC) patterns from aerial and satellite imagery. Despite recent progress with convolutional neural networks (CNNs) and vision transformers (ViTs), the task remains challenging due to variations in spatial resolution, viewpoint, orientation, and background conditions, which often reduce the generalization ability of existing models. To address these challenges, this paper proposes a lightweight architecture based on the convolutional mixer paradigm. The model alternates between spatial mixing through depthwise convolutions at multiple scales and channel mixing through pointwise operations, enabling efficient extraction of both local and contextual information while keeping the number of parameters and computations low. Extensive experiments were conducted on the AID and EuroSAT benchmarks. The proposed model achieved overall accuracy, average accuracy, and Kappa values of 74.7%, 74.57%, and 73.79 on the AID dataset, and 93.90%, 93.93%, and 93.22 on EuroSAT, respectively. These results demonstrate that the proposed approach provides a good balance between accuracy and efficiency compared with widely used CNN- and transformer-based models. Code will be publicly available on: https://github.com/mqalkhatib/SceneMixer
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。