Owing to the powerful data representation ability of deep learning (DL) techniques, tremendous progress has been recently made in hyperspectral image (HSI) classification. Convolutional neural network (CNN), as a main part of the DL family, has been proven to be considerably effective to extract spatial–spectral features for HSIs. Nevertheless, its classification performance, to a great extent, depends on the quality and quantity of samples in the network training process. To select those samples, either labeled or unlabeled, which can be used to enhance the generalization ability of CNNs and further improve the classification accuracy, we propose an iterative semi-supervised CNNs framework by means of active learning and superpixel segmentation techniques, dubbed as semi-active CNNs (SA-CNNs), for HSI classification. More specifically, we start to pretrain a CNN-based model on a small-scale unbiased labeled set and infer unlabeled data using the trained model, i.e., generating pseudolabels. Then, the reliable samples, which consist of two parts: high label homogeneity and most informativeness, are actively selected from superpixel segments. These selected labeled and unlabeled samples with their labels and pseudolabels are refed into the next-round network training. Moreover, three different schedules, i.e., log-, exp-, and linear-schedules, are progressively adopted to fully explore their potentials in sample selection, until a labeling budget is finally reached. Extensive experiments are conducted on three benchmark HSI datasets, demonstrating substantial performance improvements of the proposed SA-CNNs over other similar competitors.

中文翻译：

---

用于高光谱图像分类的半主动卷积神经网络

由于深度学习（DL）技术强大的数据表示能力，最近在高光谱图像（HSI）分类方面取得了巨大进展。卷积神经网络 (CNN) 作为 DL 系列的主要部分，已被证明在提取 HSI 的空间光谱特征方面非常有效。然而，其分类性能在很大程度上取决于网络训练过程中样本的质量和数量。为了选择那些可用于增强 CNN 的泛化能力并进一步提高分类精度的样本，无论是标记的还是未标记的，我们通过主动学习和超像素分割技术提出了一种迭代的半监督 CNN 框架，称为半监督-active CNNs (SA-CNNs)，用于 HSI 分类。进一步来说，我们开始在小规模无偏标记集上预训练基于 CNN 的模型，并使用训练后的模型推断未标记数据，即生成伪标签。然后，由两部分组成的可靠样本：高标签同质性和信息量最大，从超像素段中主动选择。这些选择的标记和未标记样本及其标签和伪标签被引用到下一轮网络训练中。此外，逐步采用三种不同的时间表，即log-、exp-和linear-schedule，以充分挖掘它们在样本选择中的潜力，直到最终达到标记预算。在三个基准 HSI 数据集上进行了广泛的实验，证明了所提出的 SA-CNN 相对于其他类似竞争对手的显着性能改进。