变换器与卷积模型用于卫星图像时间序列作物分割的比较研究
摘要
从卫星图像时间序列(SITS)进行作物分割是农业监测和土地利用分析中的基础任务。虽然卷积神经网络(CNN)被广泛使用,但变换器架构提供了捕捉多光谱数据中空间和时间依赖性的替代机制。本文对CNN和基于变换器的分割模型进行比较研究,这些模型用于来自Sentinel-2时间序列的作物映射,包括3D U-Net、3D FPN、3D DeepLabv3,以及三种变换器架构:Swin UNETR、TSViT 和 VistaFormer,这些架构采用不同的策略来捕捉时间依赖性。在慕尼黑和洛尔迪亚数据集上的实验表明,TSViT 实现了最佳的整体结果,略胜于3D U-Net,而3D U-Net 仍然是一个强大的CNN基准。VistaFormer 提供了最佳的效率,而Swin UNETR 性能相对竞争,但不如那些显式建模时间动态的变换器。这些结果突显了SITS中时间建模的重要性:TSViT 在CNN 和将时间视为额外空间维度的方法中表现更佳,而VistaFormer 提供了强大的效率-性能权衡。
关键词
引用
@article{arxiv.2412.01944,
title = {A Comparative Study of Transformer and Convolutional Models for Crop Segmentation from Satellite Image Time Series},
author = {Mattia Gatti and Ignazio Gallo and Nicola Landro and Christian Loschiavo and Anwar Ur Rehman and Mirco Boschetti and Riccardo La Grassa},
journal= {arXiv preprint arXiv:2412.01944},
year = {2026}
}
备注
This version corrects an error in the evaluation pipeline affecting previously reported metrics. Results have been recomputed, leading to updated values and a revised conclusion: the adapted Swin UNETR model does not outperform CNN baselines. Tables, figures, and comparisons have been updated, and the analysis has been extended to include additional transformer-based models