Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field

Due to the difficulty of obtaining manual annotations for polarimetric synthetic aperture radar (PolSAR) images, the problem of analyzing these images without or with few labels has become a current challenge. Considering the scarcity of labels, this paper proposes a noise-tolerant deep clustering-based PolSAR image classification that mainly uses autoencoders to learn discriminative features. In addition, in order to improve the performance and noise resistance of this method, we adopt Markov Random Field (MRF) to enhance the smoothness of class labels. We conducted experiments on a real benchmark PolSAR image, and the results show that our method achieves state-of-the-art PolSAR image classification results without any manual annotations.