Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification

Abstract

In this paper, we propose a novel deep semi-supervised learning (SSL) method namely Teacher-Student based label propagation method (TSLP-SSL) for sea ice classification based on Sentinel-1 synthetic aperture radar (SAR) data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from limited number of labeled samples and relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea-ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semi-supervised reference methods.