Li Yao, Zhang Liyi, Chen Lei, Ma Yunpeng
School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
School of Information Engineering, Tianjin University of Commerce, Tianjin, China.
Sci Rep. 2025 Jan 28;15(1):3473. doi: 10.1038/s41598-025-87030-7.
Deep learning is a double-edged sword. The powerful feature learning ability of deep models can effectively improve classification accuracy. Still, when the training samples for each class are limited, it will not only face the problem of overfitting but also significantly affect the classification result. Aiming at this critical problem, we propose a novel model of spectral-spatial feature extraction and weighted fusion guided by superpixels. It aims to thoroughly "squeeze" and utilize the untapped spectral and spatial features contained in hyperspectral images from multiple angles and stages. Firstly, with the guidance of superpixels, we represent the hyperspectral image in the form of latent features and use the multi-band priority criterion to select the final discriminant features. Secondly, we design a pixel-based CNN and a two-scale superpixel-based GCN classification framework for weighted feature fusion. Compared with several excellent band selection methods, the superb performance of our feature extraction module is verified. In addition, under the condition of only five training samples for each class, we conducted comparative experiments with several of the state-of-the-art classification methods and verified the excellent performance of our method on three widely used data sets.
深度学习是一把双刃剑。深度模型强大的特征学习能力可以有效提高分类准确率。然而，当每个类别的训练样本有限时，它不仅会面临过拟合问题，还会显著影响分类结果。针对这一关键问题，我们提出了一种由超像素引导的光谱-空间特征提取与加权融合的新型模型。其目的是从多个角度和阶段全面“挖掘”并利用高光谱图像中未被充分利用的光谱和空间特征。首先，在超像素的引导下，我们以潜在特征的形式表示高光谱图像，并使用多波段优先级准则来选择最终的判别特征。其次，我们设计了一个基于像素的卷积神经网络和一个基于双尺度超像素的图卷积网络分类框架用于加权特征融合。与几种优秀的波段选择方法相比，验证了我们的特征提取模块的卓越性能。此外，在每个类别仅有五个训练样本的条件下，我们与几种当前最先进的分类方法进行了对比实验，并在三个广泛使用的数据集上验证了我们方法的优异性能。
