CONSS: Contrastive Learning Approach for Semi-Supervised Seismic Facies Classification
This addresses the challenge of labor-intensive labeling for 3D seismic data in geophysics, though it is incremental as it builds on existing semi-supervised and contrastive learning techniques.
The authors tackled the problem of seismic facies classification by proposing CONSS, a semi-supervised method using pixel-level contrastive learning, which achieves state-of-the-art performance on the F3 survey using only 1% of original annotations.
Recently, seismic facies classification based on convolutional neural networks (CNN) has garnered significant research interest. However, existing CNN-based supervised learning approaches necessitate massive labeled data. Labeling is laborious and time-consuming, particularly for 3D seismic data volumes. To overcome this challenge, we propose a semi-supervised method based on pixel-level contrastive learning, termed CONSS, which can efficiently identify seismic facies using only 1% of the original annotations. Furthermore, the absence of a unified data division and standardized metrics hinders the fair comparison of various facies classification approaches. To this end, we develop an objective benchmark for the evaluation of semi-supervised methods, including self-training, consistency regularization, and the proposed CONSS. Our benchmark is publicly available to enable researchers to objectively compare different approaches. Experimental results demonstrate that our approach achieves state-of-the-art performance on the F3 survey.