Artzai Picón, Pablo Galan
Hyperspectral imaging, a rapidly evolving field, has witnessed the ascendancy of deep learning techniques, supplanting classical feature extraction and classification methods in various applications. However, many researchers employ arbitrary architectures for hyperspectral image processing, often without rigorous analysis of the interplay between spectral and spatial information. This oversight neglects the implications of combining these two modalities on model performance, consumption, and inference time. This paper evaluates the impact of including different spatial (visual texture) and spectral (captured spectral information) features on deep learning architectures for hyperspectral image segmentation. To this end, it presents different architectural configurations with varying levels of spectral and spatial information and are evaluated in terms of identification performance, energy consumption, and inference time. Additionally, the transferability of knowledge from large pre-trained image foundation models, originally designed for RGB images, to the hyperspectral domain is explored. Results show that incorporating spatial information alongside spectral data leads to improved segmentation results.
@article{e63bfe0e-43e6-4bf5-aabb-f80b4035075d,
title={On the analysis of adapting deep learning met 2025 Spectrochimica Acta Part },
author={Artzai Picón and Pablo Galan},
year={2026},
language={en}
}TY - JOUR TI - On the analysis of adapting deep learning met 2025 Spectrochimica Acta Part AU - Artzai Picón AU - Pablo Galan PY - 2026 LA - en ER -
The leachability tests for manufacturing scrap TV boards (STVB) have indicated the release of metals beyond the limit levels with potential problems f
R. Hischier, P. Wa¨ger
The production of electrical and electronic equipment (EEE) is one of the fastest growing markets in the world, leading to an expected increase in was
Naohito Hayashi, Shigeki Koyanaka
In an attempt to select an efficient recycling process for waste electrical and electronic equipment based on the value of individual products, we are
F. Wagner, J.R. Peeters
The closed-loop recycling of PolyCarbonate/Acrylonitrile Styrene Acrylate (PC/ASA) housings from post-consumer payment terminals that are subject to a
Huihui Liu, Ming Lei
It is quite common to find both formal and informal sectors for processing waste electrical and electronic equipment (WEEE) in many emerging countries
Oyuna Tsydenova, Magnus Bengtsson
This review paper summarizes the existing knowledge on the chemical hazards associated with recycling and other end-of-life treatment options of waste