Matches in SemOpenAlex for { <https://semopenalex.org/work/W2937096868> ?p ?o ?g. }
- W2937096868 abstract "Seismic image analysis plays a crucial role in a wide range of industrial applications and has been receiving significant attention. One of the essential challenges of seismic imaging is detecting subsurface salt structure which is indispensable for identification of hydrocarbon reservoirs and drill path planning. Unfortunately, exact identification of large salt deposits is notoriously difficult and professional seismic imaging often requires expert human interpretation of salt bodies. Convolutional neural networks (CNNs) have been successfully applied in many fields, and several attempts have been made in the field of seismic imaging. But the high cost of manual annotations by geophysics experts and scarce publicly available labeled datasets hinder the performance of the existing CNN-based methods. In this work, we propose a semi-supervised method for segmentation (delineation) of salt bodies in seismic images which utilizes unlabeled data for multi-round self-training. To reduce error amplification during self-training we propose a scheme which uses an ensemble of CNNs. We show that our approach outperforms state-of-the-art on the TGS Salt Identification Challenge dataset and is ranked the first among the 3234 competing methods." @default.
- W2937096868 created "2019-04-25" @default.
- W2937096868 creator A5053620423 @default.
- W2937096868 creator A5066271724 @default.
- W2937096868 creator A5073414105 @default.
- W2937096868 date "2019-04-08" @default.
- W2937096868 modified "2023-09-23" @default.
- W2937096868 title "Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks" @default.
- W2937096868 cites W1493009343 @default.
- W2937096868 cites W1901129140 @default.
- W2937096868 cites W1910501430 @default.
- W2937096868 cites W1948751323 @default.
- W2937096868 cites W2063143741 @default.
- W2937096868 cites W2101210369 @default.
- W2937096868 cites W2106401878 @default.
- W2937096868 cites W2110039350 @default.
- W2937096868 cites W2136504847 @default.
- W2937096868 cites W2147800946 @default.
- W2937096868 cites W2194775991 @default.
- W2937096868 cites W2283415767 @default.
- W2937096868 cites W2308529009 @default.
- W2937096868 cites W2321533354 @default.
- W2937096868 cites W2329576811 @default.
- W2937096868 cites W2518108298 @default.
- W2937096868 cites W2521278198 @default.
- W2937096868 cites W2549139847 @default.
- W2937096868 cites W2572767459 @default.
- W2937096868 cites W2600148249 @default.
- W2937096868 cites W2770429219 @default.
- W2937096868 cites W2781055951 @default.
- W2937096868 cites W2782757030 @default.
- W2937096868 cites W2788970402 @default.
- W2937096868 cites W2795587607 @default.
- W2937096868 cites W2795912842 @default.
- W2937096868 cites W2804488433 @default.
- W2937096868 cites W2807654303 @default.
- W2937096868 cites W2807914764 @default.
- W2937096868 cites W2810812775 @default.
- W2937096868 cites W2883451034 @default.
- W2937096868 cites W2883718074 @default.
- W2937096868 cites W2886381392 @default.
- W2937096868 cites W2890060893 @default.
- W2937096868 cites W2891691398 @default.
- W2937096868 cites W2892266157 @default.
- W2937096868 cites W2902454146 @default.
- W2937096868 cites W2907346126 @default.
- W2937096868 cites W2949558113 @default.
- W2937096868 cites W2951393419 @default.
- W2937096868 cites W2959750002 @default.
- W2937096868 cites W2962877362 @default.
- W2937096868 cites W2963420272 @default.
- W2937096868 cites W2964037671 @default.
- W2937096868 cites W2964178561 @default.
- W2937096868 cites W2964288706 @default.
- W2937096868 cites W3118608800 @default.
- W2937096868 cites W343636949 @default.
- W2937096868 doi "https://doi.org/10.48550/arxiv.1904.04445" @default.
- W2937096868 hasPublicationYear "2019" @default.
- W2937096868 type Work @default.
- W2937096868 sameAs 2937096868 @default.
- W2937096868 citedByCount "5" @default.
- W2937096868 countsByYear W29370968682019 @default.
- W2937096868 countsByYear W29370968682020 @default.
- W2937096868 countsByYear W29370968682021 @default.
- W2937096868 crossrefType "posted-content" @default.
- W2937096868 hasAuthorship W2937096868A5053620423 @default.
- W2937096868 hasAuthorship W2937096868A5066271724 @default.
- W2937096868 hasAuthorship W2937096868A5073414105 @default.
- W2937096868 hasBestOaLocation W29370968681 @default.
- W2937096868 hasConcept C116834253 @default.
- W2937096868 hasConcept C119857082 @default.
- W2937096868 hasConcept C127313418 @default.
- W2937096868 hasConcept C153180895 @default.
- W2937096868 hasConcept C154945302 @default.
- W2937096868 hasConcept C165205528 @default.
- W2937096868 hasConcept C202444582 @default.
- W2937096868 hasConcept C33923547 @default.
- W2937096868 hasConcept C41008148 @default.
- W2937096868 hasConcept C59822182 @default.
- W2937096868 hasConcept C79675319 @default.
- W2937096868 hasConcept C81363708 @default.
- W2937096868 hasConcept C86803240 @default.
- W2937096868 hasConcept C89600930 @default.
- W2937096868 hasConcept C9652623 @default.
- W2937096868 hasConceptScore W2937096868C116834253 @default.
- W2937096868 hasConceptScore W2937096868C119857082 @default.
- W2937096868 hasConceptScore W2937096868C127313418 @default.
- W2937096868 hasConceptScore W2937096868C153180895 @default.
- W2937096868 hasConceptScore W2937096868C154945302 @default.
- W2937096868 hasConceptScore W2937096868C165205528 @default.
- W2937096868 hasConceptScore W2937096868C202444582 @default.
- W2937096868 hasConceptScore W2937096868C33923547 @default.
- W2937096868 hasConceptScore W2937096868C41008148 @default.
- W2937096868 hasConceptScore W2937096868C59822182 @default.
- W2937096868 hasConceptScore W2937096868C79675319 @default.
- W2937096868 hasConceptScore W2937096868C81363708 @default.
- W2937096868 hasConceptScore W2937096868C86803240 @default.
- W2937096868 hasConceptScore W2937096868C89600930 @default.
- W2937096868 hasConceptScore W2937096868C9652623 @default.
- W2937096868 hasLocation W29370968681 @default.