Majid Seydgar, Shahryar Rahnamayan, Pedram Ghamisi, and Azam Asilian Bidgoli
Deep neural networks (DNNs) show impressive performance for hyperspectral image (HSI) classification when abundant labeled samples are available. The problem is that HSI sample annotation is extremely costly and the budget for this task is usually limited. To reduce the reliance on labeled samples, deep semisupervised learning (SSL), which jointly learns from labeled and unlabeled samples, has been introduced in the literature. However, learning robust and discriminative features from unlabeled data is a challenging task due to various noise effects and ambiguity of unlabeled samples. As a result, recent advances are constrained, mainly in the pretraining or warm-up stage. In this article, we propose a deep probabilistic framework to generate reliable pseudo-labels to explicitly learn discriminative features from unlabeled samples. The generated pseudo-labels of our proposed framework can be fed to various DNNs to improve their generalization capacity. Our proposed framework takes only ten labeled samples per class to represent the label set as an uncertainty-aware distribution. We use the Gaussian distribution to represent the uncertainty of the label set in the latent space. The pseudo-labels are then generated for those unlabeled samples whose feature values match the distribution with high probability. By performing extensive experiments on four publicly available datasets, we show that our framework can generate reliable pseudo-labels to significantly improve the generalization capacity of several state-of-the-art DNNs. In addition, we introduce a new DNN for HSI classification that demonstrates outstanding accuracy results in comparison with its rivals.
IEEE Transactions on Geoscience and Remote Sensing, 60, 2022-08-04.