不均衡少标签样本下基于语义自动编码网络的高光谱图像分类  

Hyperspectral Image Classification Based on Improved Semantic AutoEncoder Network in Unbalanced Small-Sized Labeled Samples

作　　者：孙宝刚[1] 何国斌 SUN Baogang;HE Guobin(School of Computer Science and Engineering,Chongqing College of Humanities Science&Technology,Chongqing 401524,China;College of Computer&Information Science Southwest University,Chongqing 400715,China)

机构地区：[1]重庆人文科技学院计算机工程学院,重庆合川401524 [2]西南大学计算机与信息科学学院,重庆北碚400715

出　　处：《红外技术》2025年第4期429-436,共8页Infrared Technology

基　　金：国家自然科学基金项目(31071319);2022年重庆教委研究项目(22SKGH493)。

摘　　要：为了提升不均衡少标签样本下高光谱图像分类性能,本文提出了一种改进的语义自动编码网络,该网络首先将高光谱的类别标签信息引入到语义自编码网络模型中,通过将不同数据集的原始数据及标签信息分别映射至同一特征空间以建立已知类别和未知类别的关联,然后将该对应关系应用于未知数据集进行标签推理,并构建基于图正则化项的目标函数以保存数据集中特征流形结构,最后采用交替方向乘子法将全局问题分解为多个较小、较容易求解的局部子问题,最终获得全局最优解。实验选取3个具有不同的光谱维度、光谱带数量和土地覆盖类型的高光谱数据集进行处理,可以满足实验数据的多样性。结果表明,本文所提方法的分类结果具有较高的分类精度,其分类结果与基准结果比较相近,适合工程上对非均衡高光谱图像数据分类。To improve the classification performance of hyperspectral images with unbalanced,few-labeled samples,an improved semantic autoencoder network is proposed in this paper.This network first introduces hyperspectral category-label information into the semantic autoencoder model,establishing the association between known and unknown categories by mapping the original data and label information of different datasets to the same feature space.It then maps the training dataset features to the unified embedding space to learn the correspondence between the visual features and the semantic features of the category labels.Finally,an objective function based on a graph regularization term is constructed to preserve the feature manifold structure in the dataset,and the global problem is decomposed into several smaller,more manageable local subproblems using the alternating direction multiplier method to obtain the global optimal solution.Three hyperspectral datasets with different spectral dimensions,numbers of spectral bands,and land cover types were selected to ensure the diversity of the experimental data.The results showed that the proposed method achieved better classification accuracy with a small number of labeled samples compared with other state-of-the-art methods,making it suitable for the engineering classification of unbalanced hyperspectral image data.

关 键 词：高光谱图像 地物分类 深度学习 语义自动编码网络 语义关联 特征映射 

分 类 号：TN958[电子电信—信号与信息处理]