English

HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models

Computer Vision and Pattern Recognition 2026-05-20 v3

Abstract

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.

Keywords

Cite

@article{arxiv.2505.12217,
  title  = {HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models},
  author = {Aryan Das and Tanishq Rachamalla and Pravendra Singh and Koushik Biswas and Vinay Kumar Verma and Salvador Garcia and Antonio Plaza and Swalpa Kumar Roy},
  journal= {arXiv preprint arXiv:2505.12217},
  year   = {2026}
}

Comments

Accepted for publication in IEEE Geoscience and Remote Sensing Magazine (GRSM), 2026

R2 v1 2026-07-01T02:19:09.349Z