高光谱图像模型：技术报告

中文摘要 AI 辅助

高光谱遥感已在多种深度学习范式中取得进展，包括光谱空间CNN、视觉Transformer、Mamba、图神经网络、Kolmogorov-Arnold网络以及自监督掩码自编码。然而，进展仍受制于碎片化的代码库、不兼容的张量约定和非标准化的评估。高光谱图像模型通过一个模块化框架解决了这些挑战，该框架统一了六个范式中的55个代表性模型，具有通用注册表、自动4D/5D张量适配和标准化构造函数。它整合了来自机载、星载、无人机和火星CRISM传感器的24个基准场景，支持缓存、标签重映射、PCA、显式波段选择或原始光谱、可选的空间最大池化以及任意PxP补丁提取。为防止重叠窗口导致的精度虚高，它支持类别平衡的随机划分和具有切比雪夫保护带的空间不相交区域阻塞，以消除训练测试像素重叠。实验使用单一URL，具有确定性种子和完整来源记录，生成LaTeX基准表和分类图。在1,320个模型场景评估和6,600次种子运行中，场景难度主导架构，平均精度从博茨瓦纳的96.40%到休斯顿2018的56.70%，范式均值间有15个百分点的差距。没有范式普遍占优，而低于1M参数的模型可以匹配大两个数量级的架构。代码公开于提供的URL。

英文摘要

Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and self supervised masked autoencoding. Yet progress remains hindered by fragmented repositories, incompatible tensor conventions, and non standardized evaluation. Hyperspectral Image Models addresses these challenges through a modular framework unifying 55 representative models across six paradigms with a common registry, automatic 4D/5D tensor adaptation, and standardized constructors. It integrates 24 benchmark scenes from Airborne, Spaceborne, UAV, and Mars CRISM sensors, with caching, label remapping, PCA, explicit band selection or raw spectra, optional spatial max pooling, and arbitrary PxP patch extraction. To prevent inflated accuracy from overlapping windows, it supports class balanced random partitioning and spatially disjoint regional blocking with Chebyshev guard bands that eliminate train test pixel overlap. Experiments use a single config with deterministic seeds and complete provenance, generating LaTeX benchmark tables and classification maps. Across 1,320 model scene evaluations and 6,600 seeded runs, scene difficulty dominates architecture, with mean accuracy ranging from 96.40% on Botswana to 56.70% on Houston 2018, versus a 15 point spread across paradigm means. No paradigm universally dominates, while sub 1 M parameter models can match architectures two orders of magnitude larger. Code is publicly available at https://github.com/Tanishq251/Hyperspectral-Image-Models.

发表机构

• Siddhartha Academy of Higher Education（悉达多高等教育学院）
• Vellore Institute of Technology（韦洛尔理工学院）
• Indira Gandhi National Open University（英迪拉·甘地国立开放大学）
• Tezpur University（提斯浦尔大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Documentation and benchmark library for hyperspectral image models