Continuously improving the accuracy is a hot topic in hyperspectral image (HSI) classification with small-scale samples, due to the high label noise of traditional labeling systems and the high cost of expert labeling systems. We focus on constructing a smaller and more informative training sample set, so an iterative sample selection method guided by uncertainty measurement (ISS-Un) is proposed. The method learns shallow and deep features in the spectral and spatial domains via a convolutional neural network (CNN), where an uncertainty measurement algorithm such as least confidence (LC), marginal sampling (MS) or entropy (Ent) is used to iteratively select high-quality samples for the training set. In addition, we propose a more efficient uncertainty measurement algorithm named margin-entropy fusion (MEF) algorithm to integrate multiple-criteria information. The proposed method is compared with the conventional random sampling method. Experimental results on three HSI datasets show that the proposed ISS-Un method can significantly alleviate the redundancy of training samples and form a more compact and efficient training set, thus improving the classification performance of pixel-oriented HSI. Meanwhile, training sets constructed based on different uncertainty measurement algorithms are applied to five popular CNN models to verify the quality and generalizability of the selected samples. The results show that these training sets work better than random training sampling. Moreover, the proposed MEF algorithm outperforms the LC, MS, and Ent algorithms in selecting samples and is the main recommended scheme.

中文翻译：

---

通过浅卷积神经网络进行不确定性测量引导的迭代样本选择用于高光谱图像分类

由于传统标注系统的高标签噪声和专家标注系统的高成本，不断提高精度是小样本高光谱图像（HSI）分类的热门话题。我们专注于构建更小、信息量更大的训练样本集，因此提出了一种以不确定性测量为指导的迭代样本选择方法（ISS-Un）。该方法通过卷积神经网络 (CNN) 学习光谱和空间域中的浅层和深层特征，其中使用最小置信度 (LC)、边际采样 (MS) 或熵 (Ent) 等不确定性测量算法来迭代选择训练集的高质量样本。此外，我们提出了一种更有效的不确定性测量算法，称为边际熵融合（MEF）算法来整合多准则信息。将所提出的方法与传统的随机抽样方法进行了比较。在三个 HSI 数据集上的实验结果表明，所提出的 ISS-Un 方法可以显着减轻训练样本的冗余，形成更紧凑、更高效的训练集，从而提高面向像素的 HSI 的分类性能。同时，将基于不同不确定性测量算法构建的训练集应用于五个流行的 CNN 模型，以验证所选样本的质量和泛化性。结果表明，这些训练集比随机训练抽样效果更好。此外，所提出的 MEF 算法优于 LC、MS、