Traditional change detection (CD) algorithms cannot meet the requirements of today’s high resolution remote sensing images (HR). Recently, deep learning-based CD has become a popular research topic. However, there are not many annotated samples for training deep learning (DL) models. Patch-based algorithm has become an important research direction in CD in response to the lack of training datasets, but the optimal patch size is relatively small and difficult to determine, which limits the use of spatial information and the extension of deep network. In this paper, we develop a feature-regularized mask DeepLab (FRM-DeepLab) for HRCD. First, a mask-based framework (MaskNet) that uses a few annotated samples to update model parameters is introduced. Based on MaskNet, we design a Mask-DeepLab to make full use of HR. Last, the deep features of unlabeled areas are extracted by an autoencoder as auxiliary information, and those features are concatenated in the middle-level features extracted by Mask-DeepLab to alleviate the influences of overfitting caused by small-scale samples. The algorithm is verified on three HRCD datasets. The visualization and quantitative analysis of the experiment results figure that this algorithm can implement significant performance improvement.

传统的变化检测（CD）算法无法满足当今高分辨率遥感图像（HR）的要求。最近，基于深度学习的 CD 已经成为一个热门的研究课题。但是，用于训练深度学习 (DL) 模型的带注释的样本并不多。针对训练数据集的缺乏，基于patch的算法成为CD的一个重要研究方向，但最优patch大小相对较小且难以确定，限制了空间信息的使用和深度网络的扩展。在本文中，我们为 HRCD 开发了一个特征正则化掩码 DeepLab (FRM-DeepLab)。首先，介绍了一个基于掩码的框架（MaskNet），它使用一些带注释的样本来更新模型参数。基于MaskNet，我们设计了一个Mask-DeepLab来充分利用HR。最后的，自编码器提取未标记区域的深层特征作为辅助信息，并将这些特征串联在Mask-DeepLab提取的中层特征中，以减轻小规模样本引起的过拟合的影响。该算法在三个 HRCD 数据集上得到验证。实验结果的可视化和定量分析表明，该算法可以实现显着的性能提升。