Metraipolis › archive › dc_ef2d62f8dc3d
Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks — arXiv:2608.16241
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16241
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:44:21.845Z
- SHA-256 of the archived text
336c26491578df48db61f73109d56b9b526d8496c5fb7821cb4bea9b5c2b1d0e- Stable URL of this page
https://metraipolis.com/documento/dc_ef2d62f8dc3d
How to cite
Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks — arXiv:2608.16241 — arXiv (en), https://arxiv.org/abs/2608.16241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef2d62f8dc3d (Metraipolis archive dc_ef2d62f8dc3d, sha256 336c26491578df48db61f73109d56b9b526d8496c5fb7821cb4bea9b5c2b1d0e)
BibTeX
@misc{dcef2d62f8dc3d,
title = {Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks — arXiv:2608.16241},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16241},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef2d62f8dc3d; sha256 336c26491578df48db61f73109d56b9b526d8496c5fb7821cb4bea9b5c2b1d0e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feature extraction for hyperspectral image classification is conventionally addressed using rigid tensor decompositions that fail to capture complex spatio-spectral interdependencies, or heavily parameterized convolutional neural networks that are computationally expensive. To overcome these limitations, this work introduces the Holistic Multivariance Decomposition (HMD) framework as a novel, end-to-end differentiable neural network layer. By explicitly separating independent single mode variations from cooperative higher dimensional interactions via learnable, matrix valued supports, the proposed HMD-0, HMD-1 and HMD-2 approximants are optimized jointly with a downstream classifier via backpropagation. Comprehensive evaluations across three benchmark HS datasets demonstrate that the higher level HMD layers achieve superior classification accuracy compared to classical learnable tensor baselines, including Tucker, Canonical Polyadic, and Tensor Train decompositions. Furthermore, HMD-1 and HMD-2 achieve a generalization capacity and training stability comparable to standard 2D and 3D-CNNs while requiring significantly fewer feature extractor parameters. These results demonstrate that the HMD framework provides a structurally robust substitute for traditional convolution in multidimensional HS image classification, offering high parameter efficiency and stability throughout the optimization process. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2608.16241 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T19:02:44.302Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).