MD Loss: Efficient Training of 3D Seismic Fault Segmentation Network under Sparse Labels by Weakening Anomaly Annotation

1 code implementation • 11 Oct 2021 • YiMin Dou, Kewen Li, Jianbing Zhu, Timing Li, Shaoquan Tan, Zongchao Huang

Recently, training 3D fault segmentation using sparse manual 2D slices is thought to yield promising results, but manual labeling has many false negative labels (abnormal annotations), which is detrimental to training and consequently to detection performance.

Fault Detection Image Segmentation +2