Search Results
Attention-Based 3D Seismic Fault Segmentation Training ...
arXiv
https://arxiv.org › cs
arXiv
https://arxiv.org › cs
by YM Dou2021Cited by 38 — In this study, we present lambda-BCE and lambda-smooth L1loss to effectively train 3D-CNN by some slices from 3D seismic data.
Seismic Fault Segmentation via 3D-CNN Training by a Few ...
ResearchGate
https://www.researchgate.net › ... › Labeling
ResearchGate
https://www.researchgate.net › ... › Labeling
Sep 7, 2024 — Qualitative experiments show that our method can extract 3D seismic features from a few 2D slices labels on real data, to segment a complete ...
Seismic Fault Segmentation via 3D-CNN Training by a Few 2D ...
CatalyzeX
https://www.catalyzex.com › paper › seismic-fault-segm...
CatalyzeX
https://www.catalyzex.com › paper › seismic-fault-segm...
The experiment proves the effectiveness of our loss function and attention module, it also shows that our method can extract 3D seismic features from a few 2D ...
Seismic Fault Segmentation via 3D-CNN Training by a Few ...
DeepAI
https://deepai.org › publication › seismic-fault-segment...
DeepAI
https://deepai.org › publication › seismic-fault-segment...
May 9, 2021 — Our method can extract 3D seismic features from a few 2D slices labels on real data, to segment a complete fault volume.
Seismic Fault Segmentation via 3D-CNN Training by a Few ...
DBLP
https://dblp.org › rec › journals › corr › abs-2105-03857
DBLP
https://dblp.org › rec › journals › corr › abs-2105-03857
May 14, 2021 — Bibliographic details on Seismic Fault Segmentation via 3D-CNN Training by a Few 2D Slices Labels.
(PDF) Attention-Based 3-D Seismic Fault Segmentation ...
ResearchGate
https://www.researchgate.net › ... › Geophysics › Seismics
ResearchGate
https://www.researchgate.net › ... › Geophysics › Seismics
Oct 8, 2021 — In this study, we presented λ-binary cross-entropy (BCE) and λ-smooth L₁ loss to effectively train 3D-CNN by some slices from 3-D seismic volume ...
Attention-Based 3-D Seismic Fault Segmentation Training ...
Semantic Scholar
https://www.semanticscholar.org › paper › Attention-Ba...
Semantic Scholar
https://www.semanticscholar.org › paper › Attention-Ba...
... train 3D-CNN by some slices from 3-D seismic volume label, so that the model can learn the segmentation of 3- D seismic data from a few 2-D slices. Expand.
Attention-Based 3D Seismic Fault Segmentation Training by a ...
arXiv
https://ar5iv.labs.arxiv.org › html
arXiv
https://ar5iv.labs.arxiv.org › html
We found that under our method, using a few 2D slices training can achieve model performance similar to using 3D volume labels. In summary, we propose an ...
A new method for automatic seismic fault detection using ...
SEG Library
https://library.seg.org › doi › segam2018-2995894
SEG Library
https://library.seg.org › doi › segam2018-2995894
by B Guo2018Cited by 80 — Our network is trained with human-labeled 2D images sliced from 3D cubes, where each pixel is labeled as either fault or non-fault. After training, the CNN ...
Fault-Seg-Net: A method for seismic fault segmentation ...
ScienceDirect.com
https://www.sciencedirect.com › article › abs › pii
ScienceDirect.com
https://www.sciencedirect.com › article › abs › pii
by X Li2023Cited by 19 — In this study, an end-to-end deep learning semantic segmentation network Fault-Seg-Net is proposed to identify fault on seismic images.