Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Das, Aryan, Rachamalla, Tanishq, Singh, Pravendra, Biswas, Koushik, Verma, Vinay Kumar, Garcia, Salvador, Plaza, Antonio, Roy, Swalpa Kumar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.12217
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918510535376896
author Das, Aryan
Rachamalla, Tanishq
Singh, Pravendra
Biswas, Koushik
Verma, Vinay Kumar
Garcia, Salvador
Plaza, Antonio
Roy, Swalpa Kumar
author_facet Das, Aryan
Rachamalla, Tanishq
Singh, Pravendra
Biswas, Koushik
Verma, Vinay Kumar
Garcia, Salvador
Plaza, Antonio
Roy, Swalpa Kumar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12217
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models
Das, Aryan
Rachamalla, Tanishq
Singh, Pravendra
Biswas, Koushik
Verma, Vinay Kumar
Garcia, Salvador
Plaza, Antonio
Roy, Swalpa Kumar
Computer Vision and Pattern Recognition
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.
title HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12217