Seed-to-Semantics: Few-Shot Prototype-Guided Progressive Learning for Hyperspectral and LiDAR Classification
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 7597-7611
Abstract
Deep learning-based fusion of hyperspectral images (HSI) and LiDAR has achieved strong performance in multimodal remote sensing classification, but its success is heavily constrained by the high cost of pixel-wise annotation. In extremely label-scarce regimes, such as 2-5 labeled samples per class, conventional deep models are prone to severe overfitting, while standard semi-supervised learning (SSL) methods often suffer from confirmation bias because pseudo-labels are generated from unstable early-stage representations. To address these challenges, we propose Prototype-Guided Progressive Learning (PGPL), a unified framework for few-shot HSI-LiDAR classification. Instead of relying solely on model confidence in latent space, PGPL first constructs a reliable initialization pool directly in the original data domain using spectral-angle and elevation-consistency cues, and then progressively expands the training set through class-balanced pseudo-label admission and temporal confidence stabilization. In this way, the framework improves pseudo-label reliability during both initialization and subsequent self-training. Extensive experiments on three benchmark datasets demonstrate that PGPL consistently outperforms state-of-the-art supervised and semi-supervised baselines under the corresponding 2-5-shot settings, achieving overall accuracy gains of 4.64% points on Houston, 1.16% on Trento, and 3.92% on MUUFL over the strongest competing methods, while also yielding higher pseudo-label purity. The source code will be publicly available at https://github.com/zhangyiyan001/PGPL.Keywords
Funding Information
- Natural Science Foundation of Jiangsu Province (BK20211201)
- China Postdoctoral Science Foundation (2021M690885)
- Basic research program of Jiangsu (BK20252043)
This publication has 37 references indexed in Scilit:
- Semi-supervised multimodal contrastive regularization network for remote sensing hyperspectral and LiDAR classificationJournal of King Saud University Computer and Information Sciences, 2025
- Adaptive multi-stage fusion of hyperspectral and LiDAR data via selective state space modelsInformation Fusion, 2025
- Pseudo-label generation guided semi-supervised network for hyperspectral image and LiDAR data classificationExpert Systems with Applications, 2025
- Cost-efficient information extraction from massive remote sensing data: When weakly supervised deep learning meets remote sensing big dataInternational Journal of Applied Earth Observation and Geoinformation, 2023
- Coupled adversarial learning for fusion classification of hyperspectral and LiDAR dataInformation Fusion, 2022
- Deep learning in multimodal remote sensing data fusion: A comprehensive reviewInternational Journal of Applied Earth Observation and Geoinformation, 2022
- CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning2021
- X-ModalNet: A semi-supervised deep cross-modal network for classification of remote sensing dataISPRS Journal of Photogrammetry and Remote Sensing, 2020
- FusAtNet: Dual Attention based SpectroSpatial Multimodal Fusion Network for Hyperspectral and LiDAR Classification2020
- Deep learning in remote sensing applications: A meta-analysis and reviewISPRS Journal of Photogrammetry and Remote Sensing, 2019