FMWDCT: Foreground Mixup Into Weighted Dual-Network Cross Training for Semisupervised Remote Sensing Road Extraction

With the development of deep learning, the application of automatic road extraction has achieved great success. However, the main challenge is how to make full use of a large number of unlabeled images to improve segmentation models and how alleviate sample imbalance in road extraction tasks. In this article, we propose a novel semisupervised remote sensing road extraction approach is defined as foreground mixup into weighted dual-network cross training (FMWDCT), which combines labeled images with unlabeled images to extract road from remote sensing images. FMWDCT is composed of dual-network cross training (DCT) and foreground pasting (FP). DCT is a new semisupervised training method and FP is an effective data perturbation method for road extraction. We first paste the foreground pixels obtained from labeled images into unlabeled images to produce mixed input images. The mixed pseudolabels are then generated by a combination of high-confidence predictions from the augmented network and labeled masks. Finally, the mixed pseudolabels are used to guide another adversarial basic network for cross training, and this basic network is used to smoothly update the augmented network that corresponds to it. The proposed FMWDCT effectively solve the overfitting problem and imbalance problem of positive and negative sample in the case of a few labeled training samples. We demonstrate the effectiveness of our method on three road extraction datasets, and achieve a better performance with few labeled data. Extensive experiments show that the proposed semisupervised method can learn latent information from the unlabeled data to improve the performance.