MD Loss: Efficient Training of 3-D Seismic Fault Segmentation Network Under Sparse Labels by Weakening Anomaly Annotation-Reference-Cited by-同舟云学术

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

Author:

Dou Yimin¹^ORCID,Li Kewen¹,Zhu Jianbing²,Li Timing³^ORCID,Tan Shaoquan²,Huang Zongchao¹

Affiliation:

1. College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China

2. Shengli Oilfield Company, SINOPEC, Dongying, China

3. College of Intelligence and Computing, Tianjin University, Tianjin, China

Funder

National Natural Science Foundation of China, Major Program

Natural Science Foundation of Shandong Province of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Earth and Planetary Sciences,Electrical and Electronic Engineering

Link

Reference40 articles.

2. UNet++: A nested U-Net architecture for medical image segmentation;zhou;Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support,2018

3. 3D U-Net: Learning dense volumetric segmentation from sparse annotation;çiçek;Proc Int Conf Med Image Comput Comput -Assist Intervent,2016

4. Segmentation loss Odyssey;ma;arXiv 2005 13449,2020

Cited by 16 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献