Confidence-Weighted Dual-Teacher Networks With Biased Contrastive Learning for Semi-Supervised Semantic Segmentation in Remote Sensing Images

Semantic segmentation of remote sensing images is vital in remote sensing technology. High-quality models for this task require a vast amount of images, and manual annotation is a process that is time-consuming and labor-intensive. Consequently, this has catalyzed the emergence of semi-supervised semantic segmentation methods. However, the complexity of foreground categories in remote sensing images poses a challenge to maintaining prediction consistency. Moreover, inherent characteristics such as intraclass variations and interclass similarities result in a certain degree of confusion among features of different classes in the feature space. This impacts the final classification results. To improve the model’s consistency and optimize the classification of categories based on features, this article proposes a new semi-supervised semantic segmentation framework that combines consistency regularization and contrastive learning (CL). In terms of consistency regularization, the proposed method incorporates dual-teacher networks, introduces ClassMix for image augmentation, and uses confidence levels to integrate the predictions from these networks. By introducing perturbations at both the network and image levels, while simultaneously maintaining consistency, the predictive prowess and generalization ability of the model are enhanced. For CL, positive-unlabeled learning (PU-Learning) is used to improve the problem of mis-sampling when selecting features. At the same time, higher biased weights are allocated to more challenging negative samples, thereby elevating the complexity of feature learning and enhancing the discriminative capability of the final feature representation space. Our extensive experiments on the ISPRS Vaihingen dataset and the challenging iSAID dataset have served to underscore the superior performance of our approach.