Semisupervised salt segmentation using mean teacher

Abstract

Detecting subsurface salt structures from seismic images is important for seismic structural analysis and subsurface modeling. Recently, deep learning has been successfully applied in solving salt segmentation problems. However, most of the studies focus on supervised salt segmentation and require numerous accurately labeled data, which are usually laborious and time-consuming to collect, especially for the geophysics community. We have adopted a semisupervised framework for salt segmentation, which requires only a small amount of labeled data. In our method, adopting the mean teacher method, we train two models sharing the same network architecture. The student model is optimized using a combination of supervised loss and unsupervised consistency loss, whereas the teacher model is the exponential moving average of the student model. We introduce the unsupervised consistency loss to better extract information from unlabeled data by constraining the network to give consistent predictions for the input data and its perturbed version. We train and test our novel semisupervised method on synthetic and real data sets. Results demonstrate that our semisupervised salt segmentation method outperforms the supervised baseline when there is a lack of labeled training data.