AuraTracer智迹闻
中文

EVENT DOSSIER

Semi-Supervised Hyperspectral Image Classification with Edge-Aware Superpixel Label Propagation and Adaptive Pseudo-Labeling

2026-09-07 12:00 Science 🔥 40.2 heat score
1sources
1days unfolding
40.2heat score
0mentions
SummaryAI generated

On September 7, 2026, arXiv cs.CV published a research paper on semi-supervised hyperspectral image classification. The study proposed a new method that combines edge-aware superpixel label propagation with adaptive pseudo-labels, aiming to improve classification performance in semi-supervised scenarios.

Related eventsRELATED EVENTS

All reports (1)SOURCES

A arXiv cs.CV en 2026-09-07 12:00

Semi-Supervised Hyperspectral Image Classification with Edge-Aware Superpixel Label Propagation and Adaptive Pseudo-Labeling

针对半监督高光谱图像分类中边界标签扩散和伪标签不稳定的问题,本文提出一种结合空间先验与动态学习机制的新框架。该框架首先设计边缘感知超像素标签传播模块,通过集成边缘强度惩罚与邻域校正策略缓解标签扩散并增强边界区域鲁棒性;其次引入动态历史融合预测方法,利用历史预测与当前结果的动态加权平滑伪标签波动;同时采用自适应三分类样本策略,分层利用易、难及模糊样本以提升伪标签质量。经四个基准数据集验证,该框架在保持时空一致性的同时实现了优异的分类性能。