Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801492038> ?p ?o ?g. }
- W2801492038 endingPage "768" @default.
- W2801492038 startingPage "748" @default.
- W2801492038 abstract "Abstract This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Challenge and the development of computer hardware, the concept of Structural ImageNet is proposed herein with four naïve baseline recognition tasks: component type identification, spalling condition check, damage level evaluation, and damage type determination. A relatively small number of images (2,000) are selected from the Structural ImageNet and manually labeled according to the four recognition tasks. In order to avoid overfitting, Transfer Learning (TL) based on VGGNet (Visual Geometry Group) is introduced and applied using two different strategies, namely feature extractor and fine‐tuning. Two experiments are designed based on properties of these two strategies to find the relative optimal model parameters and scope of application. Models obtained by both strategies indicate the promising recognition results and different application potentials where feature extractor and fine‐tuning can be respectively used for preliminary analysis and for further improvement. These results also reveal the potential uses of deep TL in image‐based structural damage recognition." @default.
- W2801492038 created "2018-05-17" @default.
- W2801492038 creator A5057186635 @default.
- W2801492038 creator A5074146436 @default.
- W2801492038 date "2018-04-16" @default.
- W2801492038 modified "2023-10-16" @default.
- W2801492038 title "Deep Transfer Learning for Image‐Based Structural Damage Recognition" @default.
- W2801492038 cites W1485843859 @default.
- W2801492038 cites W1542901595 @default.
- W2801492038 cites W1849277567 @default.
- W2801492038 cites W1928278792 @default.
- W2801492038 cites W1972604329 @default.
- W2801492038 cites W1982219759 @default.
- W2801492038 cites W2011521513 @default.
- W2801492038 cites W2019949051 @default.
- W2801492038 cites W2037174685 @default.
- W2801492038 cites W2067175639 @default.
- W2801492038 cites W2074772891 @default.
- W2801492038 cites W2097117768 @default.
- W2801492038 cites W2108598243 @default.
- W2801492038 cites W2112796928 @default.
- W2801492038 cites W2126052502 @default.
- W2801492038 cites W2128880484 @default.
- W2801492038 cites W2147800946 @default.
- W2801492038 cites W2161381512 @default.
- W2801492038 cites W2163345210 @default.
- W2801492038 cites W2165698076 @default.
- W2801492038 cites W2194775991 @default.
- W2801492038 cites W2253429366 @default.
- W2801492038 cites W2261304198 @default.
- W2801492038 cites W2295107390 @default.
- W2801492038 cites W234388709 @default.
- W2801492038 cites W2516809705 @default.
- W2801492038 cites W2556345765 @default.
- W2801492038 cites W2559316905 @default.
- W2801492038 cites W2593771152 @default.
- W2801492038 cites W2598457882 @default.
- W2801492038 cites W2748643398 @default.
- W2801492038 cites W2768955070 @default.
- W2801492038 cites W2962858109 @default.
- W2801492038 doi "https://doi.org/10.1111/mice.12363" @default.
- W2801492038 hasPublicationYear "2018" @default.
- W2801492038 type Work @default.
- W2801492038 sameAs 2801492038 @default.
- W2801492038 citedByCount "433" @default.
- W2801492038 countsByYear W28014920382018 @default.
- W2801492038 countsByYear W28014920382019 @default.
- W2801492038 countsByYear W28014920382020 @default.
- W2801492038 countsByYear W28014920382021 @default.
- W2801492038 countsByYear W28014920382022 @default.
- W2801492038 countsByYear W28014920382023 @default.
- W2801492038 crossrefType "journal-article" @default.
- W2801492038 hasAuthorship W2801492038A5057186635 @default.
- W2801492038 hasAuthorship W2801492038A5074146436 @default.
- W2801492038 hasBestOaLocation W28014920381 @default.
- W2801492038 hasConcept C108583219 @default.
- W2801492038 hasConcept C115961682 @default.
- W2801492038 hasConcept C117978034 @default.
- W2801492038 hasConcept C119857082 @default.
- W2801492038 hasConcept C127413603 @default.
- W2801492038 hasConcept C138885662 @default.
- W2801492038 hasConcept C150899416 @default.
- W2801492038 hasConcept C153180895 @default.
- W2801492038 hasConcept C154945302 @default.
- W2801492038 hasConcept C199360897 @default.
- W2801492038 hasConcept C21880701 @default.
- W2801492038 hasConcept C22019652 @default.
- W2801492038 hasConcept C2776401178 @default.
- W2801492038 hasConcept C2778012447 @default.
- W2801492038 hasConcept C41008148 @default.
- W2801492038 hasConcept C41895202 @default.
- W2801492038 hasConcept C50644808 @default.
- W2801492038 hasConceptScore W2801492038C108583219 @default.
- W2801492038 hasConceptScore W2801492038C115961682 @default.
- W2801492038 hasConceptScore W2801492038C117978034 @default.
- W2801492038 hasConceptScore W2801492038C119857082 @default.
- W2801492038 hasConceptScore W2801492038C127413603 @default.
- W2801492038 hasConceptScore W2801492038C138885662 @default.
- W2801492038 hasConceptScore W2801492038C150899416 @default.
- W2801492038 hasConceptScore W2801492038C153180895 @default.
- W2801492038 hasConceptScore W2801492038C154945302 @default.
- W2801492038 hasConceptScore W2801492038C199360897 @default.
- W2801492038 hasConceptScore W2801492038C21880701 @default.
- W2801492038 hasConceptScore W2801492038C22019652 @default.
- W2801492038 hasConceptScore W2801492038C2776401178 @default.
- W2801492038 hasConceptScore W2801492038C2778012447 @default.
- W2801492038 hasConceptScore W2801492038C41008148 @default.
- W2801492038 hasConceptScore W2801492038C41895202 @default.
- W2801492038 hasConceptScore W2801492038C50644808 @default.
- W2801492038 hasIssue "9" @default.
- W2801492038 hasLocation W28014920381 @default.
- W2801492038 hasOpenAccess W2801492038 @default.
- W2801492038 hasPrimaryLocation W28014920381 @default.
- W2801492038 hasRelatedWork W2951211570 @default.
- W2801492038 hasRelatedWork W3023427754 @default.
- W2801492038 hasRelatedWork W3099765033 @default.
- W2801492038 hasRelatedWork W3131673289 @default.
- W2801492038 hasRelatedWork W3167935049 @default.