Deep learning provides excellent potentials for hyperspectral images (HSIs) classification, but it is infamous for requiring large amount of labeled samples while the collection of high-quality labels for HSIs is extremely expensive and time-consuming. Furthermore, when the limited training samples are available, deep learning methods may suffer from over-fitting. In this work, we propose a novel collaborative learning framework for semi-supervised HSI classification with joint deep convolutional neural networks and deep clustering. Specifically, a lightweight 3D convolutional neural network (CNN) with much less parameters compared with classical 3D CNNs is designed for deep discriminative feature learning and classification. Then a deep clustering method, that is approximate rank-order clustering (AROC) algorithm, is applied to cluster deep features to generate pseudo labels for abundant unlabeled samples. Finally, we fine-tune the lightweight 3D CNN by minimizing a dual-loss (softmax loss and center loss) using both true and pseudo labels. Experimental results on three challenging HSI datasets demonstrate that the proposed method can achieve better performance than other state-of-the-art deep learning based methods and traditional HSI classification methods methods.

深度学习为高光谱图像（HSI）分类提供了极好的潜力，但是臭名昭著的是需要大量的标记样本，而HSI的高质量标记的收集却非常昂贵和耗时。此外，当有限的训练样本可用时，深度学习方法可能会过度拟合。在这项工作中，我们提出了一种新的协作学习框架，用于联合监督深度卷积神经网络和深度聚类的半监督HSI分类。具体来说，轻量级3D卷积神经网络（CNN）与经典3D CNN相比具有更少的参数，旨在进行深度区分性特征学习和分类。然后是一种深度聚类方法，即近似秩排序聚类（AROC）算法，应用于深度特征的聚类以生成大量未标记样本的伪标记。最后，我们通过使用真标签和伪标签使双损失（softmax损失和中心损失）最小化来微调轻量级3D CNN。在三个具有挑战性的HSI数据集上的实验结果表明，与其他基于最新技术的深度学习方法和传统HSI分类方法相比，该方法可以实现更好的性能。