arXiv 2505.122172026-05-19cs.CV

HyperCap：面向视觉语言模型的超光谱土地覆盖描述数据集

HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models

Department of Computer Science and Engineering, Vellore Institute of Technology（计算机科学与工程系，维洛雷理工学院）；Department of Information Technology, Siddhartha Academy of Higher Education（信息技术系，斯里达拉塔高等教育学院）；Department of Computer Science and Engineering, Indian Institute of Technology, Roorkee（计算机科学与工程系，印度理工学院罗尔基分校）；Department of Computer Science and Engineering, Indraprastha Institute of Information Technology Delhi（计算机科学与工程系，印度信息技术学院德里）；Department of Computer Science and Engineering, Indian Institute of Technology, Kanpur（计算机科学与工程系，印度理工学院坎浦尔）；Department of Computer Science and Artificial Intelligence, University of Granada（计算机科学与人工智能系，格拉纳达大学）；Hyperspectral Computing Laboratory, Department of Computers and Communications, University of Extremadura（超光谱计算实验室，计算机与通信系，埃斯特拉达大学）

Aryan Das, Tanishq Rachamalla, Pravendra Singh, Koushik Biswas, Vinay Kumar Verma, Salvador Garcia, Antonio Plaza, Swalpa Kumar Roy

备注：: Accepted for publication in IEEE Geoscience and Remote Sensing Magazine (GRSM), 2026
DOI：: 10.1109/MGRS.2026.3693613

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出HyperCap数据集，通过整合光谱数据与像素级文本标注，提升遥感应用中的模型性能，为未来研究提供基础资源。

摘要：

我们介绍了HyperCap，首个大规模超光谱描述数据集，旨在提升模型在遥感应用中的性能和有效性。与传统超光谱成像（HSI）基准不同，HyperCap将光谱数据与像素级文本标注相结合，实现更深入的语义理解。该数据集通过结合自动和手动方法对四个基准数据集进行标注，确保准确性和一致性。使用最先进的编码器和多样的融合技术进行实证评估，显示出显著的分类性能提升。这些结果突显了视觉-语言学习在HSI中的潜力，并将HyperCap定位为未来研究的基础数据集。代码和数据集可在https://github.com/arya-domain/HyperCap获取。

英文摘要：

We introduce HyperCap, the first large-scale hyperspectral captioning dataset designed to enhance model performance and effectiveness in remote sensing applications. Unlike traditional hyperspectral imaging (HSI) benchmarks, HyperCap integrates spectral data with pixel-wise textual annotations, enabling deeper semantic understanding. This dataset enhances model performance in tasks like classification and feature extraction, providing a valuable resource for advanced remote sensing applications. HyperCap is constructed from four benchmark datasets and annotated through a hybrid approach combining automated and manual methods to ensure accuracy and consistency. Empirical evaluations using state-of-the-art encoders and diverse fusion techniques demonstrate significant improvements in classification performance. These results underscore the potential of vision-language learning in HSI and position HyperCap as a foundational dataset for future research in the field. The code and dataset are available at https://github.com/arya-domain/HyperCap.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。