Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation

TL;DR

This paper introduces a seismic-specific contrastive learning method that leverages the spatial context of slices within seismic volumes to improve semantic segmentation accuracy, reducing reliance on fully labeled data.

Contribution

It proposes a novel positive pair selection strategy tailored for seismic data, enhancing contrastive learning effectiveness in seismic semantic segmentation.

Findings

Outperforms state-of-the-art contrastive learning methods

Improves segmentation accuracy with less labeled data

Utilizes seismic slice position for better representation learning

Abstract

In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain. As a result, there oftentimes exists a non-trivial quantity of unlabeled data that is left unused simply because traditional deep learning methods rely on access to fully labeled volumes. To rectify this problem, contrastive learning approaches have been proposed that use a self-supervised methodology in order to learn useful representations from unlabeled data. However, traditional contrastive learning approaches are based on assumptions from the domain of natural images that do not make use of seismic context. In order to incorporate this context within contrastive learning, we propose a novel positive pair selection strategy based on the position of slices within a seismic volume. We show that the learnt representations from our method out-perform a state of the art contrastive learning methodology in a semantic segmentation task.