eess.IVNov 13, 2026

Few-Shot Open-Set Hyperspectral Pixel-Wise Classification with Spatial Aware Label Propagation

Authors: Matheus Pereira, Jefersson Santos, Laurent Najman

Organizations: UFMG, LIGM · Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil · Laboratoire d’Informatique Gaspard Monge, Université Gustave Eiffel, Noisy-le-Grand, France · KUSTAR, LIGM · 

Abstract

Pixelwise classification of hyperspectral images (HSI) is a fundamental task in remote sensing, but its deployment in real-world applications is often limited by the scarcity of labeled data and the presence of unknown classes at inference time. In this work, we propose Few-shot Open-set hyperspectral recognition from Self-Supervised Learning training (FOSSeL), a unified framework for few-shot, open-set hyperspectral pixelwise classification that does not require supervised training. The proposed approach first leverages self-supervised learning to construct a discriminative feature space from unlabeled data. Then, given a small set of labeled seed pixels, class predictions are obtained through spatially-aware graph-based label propagation over superpixel representations, enabling the joint exploitation of spectral similarity and spatial consistency. To address the open-set scenario, we introduce simple yet effective strategies to identify pixels that do not belong to the known classes. We evaluate FOSSeL on three benchmark hyperspectral datasets under multiple few-shot settings. The results show that the proposed framework achieves competitive or superior performance compared to fully supervised methods while maintaining robustness in the presence of unknown classes. These findings highlight the potential of combining self-supervised feature learning with graph-based inference for practical HSI analysis in low-annotation and open-world scenarios.

Explore similar work

CardsList
  1. SoDa2: Single-Stage Open-Set Domain Adaptation via Decoupled Alignment for Cross-Scene Hyperspectral Image Classification

    May 5, 2026Yiwen Liu, Minghua Wang, Jing Yao +2Unsupervised Domain AdaptationDomain Adaptation

  2. SpectralTrain: A Universal Framework for Hyperspectral Image Classification

    Nov 20, 2025Meihua Zhou, Liping Yu, Xinyu Tong +4Hyperspectral Image ClassificationRemote Sensing

  3. Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering

    Apr 30, 2026Peifu Liu, Tingfa Xu, Jie Wang +3Soft-Label LearningHyperspectral Imaging