Metraipolis › archive › dc_390609272dce
Spectral-spatial vision test-time training for hyperspectral image classification — arXiv:2611.02364
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02364
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:56:53.685Z
- SHA-256 of the archived text
4b7bb95b3c3ef8cbe098725edda9c37dec3fd79f432b938ef4e8a88d0acbfa19- Stable URL of this page
https://metraipolis.com/documento/dc_390609272dce
How to cite
Spectral-spatial vision test-time training for hyperspectral image classification — arXiv:2611.02364 — arXiv (en), https://arxiv.org/abs/2611.02364 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_390609272dce (Metraipolis archive dc_390609272dce, sha256 4b7bb95b3c3ef8cbe098725edda9c37dec3fd79f432b938ef4e8a88d0acbfa19)
BibTeX
@misc{dc390609272dce,
title = {Spectral-spatial vision test-time training for hyperspectral image classification — arXiv:2611.02364},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02364},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_390609272dce; sha256 4b7bb95b3c3ef8cbe098725edda9c37dec3fd79f432b938ef4e8a88d0acbfa19},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02364. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hyperspectral image (HSI) classification requires the representation of contiguous spectral signatures and spatial context under limited labeled supervision. Vision test-time training (TTT) offers an alternative to fixed-weight token mixing by performing self-supervised inner-model updates on the input sequence, but its application to center-pixel HSI classification remains insufficiently characterized. We present ViTTT-HSI, a spectral-spatial adaptation of the vision test-time training (ViT3) architecture. A spectral-aware embedding stem extracts ordered-band information using spectral convolution and forms spatial tokens without reducing their spatial resolution. Two ViT3-based TTT encoder blocks perform patch-conditioned token mixing, followed by the fusion of center-pixel and neighborhood-average features for classification. We evaluate the framework on Indian Pines, Pavia University, Salinas, and Houston 2013 using ten random seeds and dataset-specific training fractions of 1% or 5%. The mean overall accuracies are 97.6390%, 98.8753%, 99.3292%, and 98.4283%, respectively. Ablations reveal a substantial contribution from the TTT inner update on Indian Pines and a smaller positive contribution on Pavia University, while the relative benefits of the spectral stem and feature fusion depend on the dataset. The results demonstrate the feasibility of using patch-conditioned vision TTT for spectral--spatial HSI classification and highlight the role of the inner adaptation mechanism. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.02364 — 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 2026-11-03T18:16:53.118Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).