Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192598395> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3192598395 endingPage "336" @default.
- W3192598395 startingPage "336" @default.
- W3192598395 abstract "Convolutional neural networks (CNN) are currently the most widely used tool for the classification of images, especially if such images have large within- and small between- group variance. Thus, one of the main factors driving the development of CNN models is the creation of large, labelled computer vision datasets, some containing millions of images. Thanks to transfer learning, a technique that modifies a model trained on a primary task to execute a secondary task, the adaptation of CNN models trained on such large datasets has rapidly gained popularity in many fields of science, geosciences included. However, the trade-off between two main components of the transfer learning methodology for geoscience images is still unclear: the difference between the datasets used in the primary and secondary tasks; and the amount of available data for the primary task itself. We evaluate the performance of CNN models pretrained with different types of image datasets—specifically, dermatology, histology, and raw food—that are fine-tuned to the task of petrographic thin-section image classification. Results show that CNN models pretrained on ImageNet achieve higher accuracy due to the larger number of samples, as well as a larger variability in the samples in ImageNet compared to the other datasets evaluated." @default.
- W3192598395 created "2021-08-16" @default.
- W3192598395 creator A5039160574 @default.
- W3192598395 creator A5077089326 @default.
- W3192598395 date "2021-08-11" @default.
- W3192598395 modified "2023-10-06" @default.
- W3192598395 title "Pretraining Convolutional Neural Networks for Mudstone Petrographic Thin-Section Image Classification" @default.
- W3192598395 cites W1853374870 @default.
- W3192598395 cites W1999206781 @default.
- W3192598395 cites W2098676252 @default.
- W3192598395 cites W2101926813 @default.
- W3192598395 cites W2117539524 @default.
- W3192598395 cites W2158698691 @default.
- W3192598395 cites W2165698076 @default.
- W3192598395 cites W2503066070 @default.
- W3192598395 cites W2739988913 @default.
- W3192598395 cites W2769210209 @default.
- W3192598395 cites W2792641098 @default.
- W3192598395 cites W2919115771 @default.
- W3192598395 cites W2931285398 @default.
- W3192598395 cites W2948930564 @default.
- W3192598395 cites W2976736125 @default.
- W3192598395 cites W2996836954 @default.
- W3192598395 cites W3034816250 @default.
- W3192598395 cites W3081524168 @default.
- W3192598395 cites W3088354476 @default.
- W3192598395 cites W3102785203 @default.
- W3192598395 cites W3151415562 @default.
- W3192598395 cites W3154228626 @default.
- W3192598395 cites W4229494842 @default.
- W3192598395 cites W4253525579 @default.
- W3192598395 doi "https://doi.org/10.3390/geosciences11080336" @default.
- W3192598395 hasPublicationYear "2021" @default.
- W3192598395 type Work @default.
- W3192598395 sameAs 3192598395 @default.
- W3192598395 citedByCount "12" @default.
- W3192598395 countsByYear W31925983952022 @default.
- W3192598395 countsByYear W31925983952023 @default.
- W3192598395 crossrefType "journal-article" @default.
- W3192598395 hasAuthorship W3192598395A5039160574 @default.
- W3192598395 hasAuthorship W3192598395A5077089326 @default.
- W3192598395 hasBestOaLocation W31925983951 @default.
- W3192598395 hasConcept C108583219 @default.
- W3192598395 hasConcept C115961682 @default.
- W3192598395 hasConcept C119857082 @default.
- W3192598395 hasConcept C120665830 @default.
- W3192598395 hasConcept C121332964 @default.
- W3192598395 hasConcept C127313418 @default.
- W3192598395 hasConcept C139807058 @default.
- W3192598395 hasConcept C150899416 @default.
- W3192598395 hasConcept C153180895 @default.
- W3192598395 hasConcept C154945302 @default.
- W3192598395 hasConcept C162324750 @default.
- W3192598395 hasConcept C17409809 @default.
- W3192598395 hasConcept C187736073 @default.
- W3192598395 hasConcept C2780451532 @default.
- W3192598395 hasConcept C41008148 @default.
- W3192598395 hasConcept C59235061 @default.
- W3192598395 hasConcept C75294576 @default.
- W3192598395 hasConcept C81363708 @default.
- W3192598395 hasConceptScore W3192598395C108583219 @default.
- W3192598395 hasConceptScore W3192598395C115961682 @default.
- W3192598395 hasConceptScore W3192598395C119857082 @default.
- W3192598395 hasConceptScore W3192598395C120665830 @default.
- W3192598395 hasConceptScore W3192598395C121332964 @default.
- W3192598395 hasConceptScore W3192598395C127313418 @default.
- W3192598395 hasConceptScore W3192598395C139807058 @default.
- W3192598395 hasConceptScore W3192598395C150899416 @default.
- W3192598395 hasConceptScore W3192598395C153180895 @default.
- W3192598395 hasConceptScore W3192598395C154945302 @default.
- W3192598395 hasConceptScore W3192598395C162324750 @default.
- W3192598395 hasConceptScore W3192598395C17409809 @default.
- W3192598395 hasConceptScore W3192598395C187736073 @default.
- W3192598395 hasConceptScore W3192598395C2780451532 @default.
- W3192598395 hasConceptScore W3192598395C41008148 @default.
- W3192598395 hasConceptScore W3192598395C59235061 @default.
- W3192598395 hasConceptScore W3192598395C75294576 @default.
- W3192598395 hasConceptScore W3192598395C81363708 @default.
- W3192598395 hasIssue "8" @default.
- W3192598395 hasLocation W31925983951 @default.
- W3192598395 hasLocation W31925983952 @default.
- W3192598395 hasOpenAccess W3192598395 @default.
- W3192598395 hasPrimaryLocation W31925983951 @default.
- W3192598395 hasRelatedWork W2738221750 @default.
- W3192598395 hasRelatedWork W2807839383 @default.
- W3192598395 hasRelatedWork W2997709384 @default.
- W3192598395 hasRelatedWork W3012393889 @default.
- W3192598395 hasRelatedWork W3018421652 @default.
- W3192598395 hasRelatedWork W3118457286 @default.
- W3192598395 hasRelatedWork W3189091156 @default.
- W3192598395 hasRelatedWork W4220996320 @default.
- W3192598395 hasRelatedWork W4285149559 @default.
- W3192598395 hasRelatedWork W4366224123 @default.
- W3192598395 hasVolume "11" @default.
- W3192598395 isParatext "false" @default.
- W3192598395 isRetracted "false" @default.
- W3192598395 magId "3192598395" @default.
- W3192598395 workType "article" @default.