Hyperspectral Image Classification With Contrastive Self-Supervised Learning Under Limited Labeled Samples
Hyperspectral Image Classification With Contrastive Self-Supervised Learning Under Limited Labeled Samples
复制标题
DOI：
10.1109/lgrs.2022.3159549
复制
发表时间：
2022
影响因子：
4.8
通讯作者：
Lin Zhao-;Wenqiang Luo;Qiming Liao;Siyuan Chen;Jianhui Wu
中科院分区：
文献类型：
--
作者：
Lin Zhao-;Wenqiang Luo;Qiming Liao;Siyuan Chen;Jianhui Wu
高光谱图像分类是遥感领域的一个研究热点。基于监督学习的方法已被广泛用于HSI分类任务，由于其强大的特征提取能力的情况下，充分标记的样本。然而，由于标记成本高或视觉解释不可靠，实际应用中具有准确标记的样品通常有限。我们引入了一个对比自监督学习（SSL）算法来实现HSI分类的问题与少数标记的样本。首先，开发了一个新的特定于HSI的增强模块来生成样本对。然后，一个基于暹罗网络的对比SSL模型被用来从这些容易访问的样本对中提取特征。最后，标记的样本被用来微调分类模型的参数，以提高分类性能。对比自监督算法的测试已经在两个广泛使用的HSI数据集上进行。实验结果表明，该算法只需要少量的标记样本就能获得上级性能。
Hyperspectral image (HSI) classification is an active research topic in remote sensing. Supervised learning-based methods have been widely used in HSI classification tasks due to their powerful feature extraction capabilities for cases of sufficiently labeled samples. However, practical applications often have limited samples with accurate labels due to the high cost of labeling or unreliable visual interpretation. We introduce a contrastive self-supervised learning (SSL) algorithm to achieve HSI classification for problems with few labeled samples. First, a new HSI-specific augmentation module is developed to generate sample pairs. Then, a contrastive SSL model based on Siamese networks is used to extract features from these easily accessible sample pairs. Finally, the labeled samples are taken to fine-tune the parameters of the classification model to boost classification performance. Tests of the contrastive self-supervised algorithm have been performed on two widely used HSI datasets. The experimental results reveal that the proposed algorithm requires a few labeled samples to achieve superior performance.