Semi-supervised classification of hyperspectral images based on contrastive learning constraint

Despite significant advancements in deep learning-based algorithms for classifying hyperspectral image (HSI), this task remains challenging when only few labeled training examples are available. In this paper, we introduce a contrastive learning constraint and propose a semi-supervised HSI classification approach. We first build a multi-scale feature extraction module, which extracts fine-grained features from a small number of labeled samples together with a huge amount of unlabeled samples. Then, by modeling contrastive constraints on the unlabeled data, we construct a contrastive subnetwork module, which can efficiently support the supervised HSI classification sub-network trained on the labeled dataset and hence enhance the generalization ability. Experimental results on two datasets demonstrate the effectiveness of the proposed semi-supervised HSI classification methods.