A Stronger Baseline for Seismic Facies Classification With Less Data

With the great success of deep learning in computer vision, the application of convolution neural network (CNN) in seismic facies classification is growing rapidly. However, most of the previous works based on pure state-of-the-art CNN architectures still suffer from coarse segmentation results. In this article, we study the challenges of seismic facies classification and propose a stronger baseline. More specifically, we propose a simple yet effective unsupervised approach named spatial pyramid sampling (SPS) to choose representative samples for training to reduce the labeling costs. Next, we propose a multimodal fusion (M2F) module to extract and fuse the edge and frequency information from selected seismic images to build a stable multimodal representation. Finally, we propose a local-to-global (L2G) module, which improves the recognition power by capturing the local relationship between pixels and enhancing the global context representation. Experimental results demonstrate that the proposed method achieves a superior performance with less labeled training data, especially for small categories.