SEUM: An Improved UniMatch Framework with Multi-Branch Spatial–Spectral Encoding and Adaptive Class-Aware Pseudo-Labeling for Semi-Supervised Hyperspectral Image Classification
Entropy · 06.11.2026 · 28 (11) · 1221
DOI: 10.3390/e28111221 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 06.11.2026. Verfasst von Wentao Jiang und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Hyperspectral image (HSI) classification is hampered by the high cost of pixel-level annotation, which leaves supervised deep networks exposed to the high-dimensional small-sample problem. Semi-supervised learning (SSL) can exploit the abundant unlabeled pixels, but SSL frameworks designed for natural images do not directly account for the spectral continuity, the coupled spatial–spectral structure and the pronounced class imbalance of HSIs. Taking the weak-to-strong consistency framework UniMatch as a starting point, this paper proposes SEUM, a semi-supervised HSI classification network with three targeted modifications. First, a multi-branch parallel convolution block with squeeze-and-excitation recalibration replaces the single-path encoder so that spatial detail, spectral mixing and salient responses are captured at several scales. Second, a dual-head classifier separates supervised classification from pseudo-label generation, and feature-level dropout is combined with input-level strong augmentation to enlarge the consistency constraint. Third, an adaptive class-aware threshold lowers the confidence requirement for under-represented classes according to their instantaneous learning state, which counteracts the self-reinforcing bias of a fixed threshold. On the Pavia University, Houston 2013 and Kennedy Space Center benchmarks with 10% labeled samples, SEUM reaches overall accuracies of 96.67%, 92.81% and 95.99%, respectively, improving on UniMatch by 0.48–2.20 percentage points and on ten supervised and semi-supervised competitors, with the largest gains on spectrally confusable and texture-rich classes, and it shows consistent improvements in average accuracy, which reflect more balanced pseudo-label utilization across the class distribution. Ablation, pseudo-label quality, label-budget and sensitivity analyses confirm that the encoder, the dual head and the adaptive threshold contribute complementary and stable improvements.
Zitieren
APA
Jiang, W., Wang, J., & Yuan, H. (2026). SEUM: An Improved UniMatch Framework with Multi-Branch Spatial–Spectral Encoding and Adaptive Class-Aware Pseudo-Labeling for Semi-Supervised Hyperspectral Image Classification. Entropy, 28(11), 1221. https://doi.org/10.3390/e28111221
Vancouver
Jiang W, Wang J, Yuan H. SEUM: An Improved UniMatch Framework with Multi-Branch Spatial–Spectral Encoding and Adaptive Class-Aware Pseudo-Labeling for Semi-Supervised Hyperspectral Image Classification. Entropy. 2026;28(11):1221. doi:10.3390/e28111221
BibTeX
@article{Jiang2026,
author = {Jiang, Wentao and Wang, Jiayue and Yuan, Heng},
title = {SEUM: An Improved UniMatch Framework with Multi-Branch Spatial–Spectral Encoding and Adaptive Class-Aware Pseudo-Labeling for Semi-Supervised Hyperspectral Image Classification},
journal = {Entropy},
year = {2026},
volume = {28},
number = {11},
pages = {1221},
doi = {10.3390/e28111221}
}
EUVIMED