FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281708623> ?p ?o ?g. }

• W4281708623 endingPage "19" @default.
• W4281708623 startingPage "1" @default.
• W4281708623 abstract "Automatic classification and retrieval of fine art collections have received much attention in recent years. In this article, we explore the applicability of convolutional neural networks (CNNs) for art-related image classification tasks. To examine how hyperparameters affect model performance, we use different hyperparameters in our experiments and find that a higher resolution and appropriate training steps with mix-up can improve model performance. To determine how transfer learning affects the final results, we systematically compare the efforts of five weight initializations of the models for different tasks. We show that fine-tuning networks pretrained on a larger dataset have better generalizability. This phenomenon shows the a priori knowledge that models learn in the real world also applies to the art world, and we call this method as big transfer learning (BiT). Through extensive experiments on fine art classification, we demonstrate that the proposed transfer learning approach outperforms the previous work by a large margin and achieves state-of-the-art performance in the art field. Furthermore, to show how computers capture features in paintings to make classifications, we visualized the results of different classification tasks to help us understand the operation mechanism of the models. Additionally, we use our models to retrieve paintings by analyzing different image similarity aspects. The results show that models can be employed to retrieve paintings even if they are computer-generated." @default.
• W4281708623 created "2022-06-13" @default.
• W4281708623 creator A5014462835 @default.
• W4281708623 creator A5067830832 @default.
• W4281708623 creator A5070386973 @default.
• W4281708623 date "2022-05-31" @default.
• W4281708623 modified "2023-10-01" @default.
• W4281708623 title "Big Transfer Learning for Fine Art Classification" @default.
• W4281708623 cites W1793977698 @default.
• W4281708623 cites W1922126009 @default.
• W4281708623 cites W1955857676 @default.
• W4281708623 cites W2017814585 @default.
• W4281708623 cites W2021087455 @default.
• W4281708623 cites W2057624659 @default.
• W4281708623 cites W2071231805 @default.
• W4281708623 cites W2108598243 @default.
• W4281708623 cites W2117539524 @default.
• W4281708623 cites W2128907386 @default.
• W4281708623 cites W2161753062 @default.
• W4281708623 cites W2165698076 @default.
• W4281708623 cites W2176950688 @default.
• W4281708623 cites W2194775991 @default.
• W4281708623 cites W2279253419 @default.
• W4281708623 cites W2302255633 @default.
• W4281708623 cites W2563117427 @default.
• W4281708623 cites W2756233723 @default.
• W4281708623 cites W2766086266 @default.
• W4281708623 cites W2771970740 @default.
• W4281708623 cites W2788919449 @default.
• W4281708623 cites W2791266670 @default.
• W4281708623 cites W2794284562 @default.
• W4281708623 cites W2795016359 @default.
• W4281708623 cites W2806587241 @default.
• W4281708623 cites W2884238566 @default.
• W4281708623 cites W2897923591 @default.
• W4281708623 cites W2903416914 @default.
• W4281708623 cites W2927066960 @default.
• W4281708623 cites W2937703861 @default.
• W4281708623 cites W2945638286 @default.
• W4281708623 cites W2962843773 @default.
• W4281708623 cites W2964332173 @default.
• W4281708623 cites W2970845903 @default.
• W4281708623 cites W2981431462 @default.
• W4281708623 cites W2984215311 @default.
• W4281708623 cites W2989596775 @default.
• W4281708623 cites W2991391304 @default.
• W4281708623 cites W3007134661 @default.
• W4281708623 cites W3090963773 @default.
• W4281708623 cites W3097217077 @default.
• W4281708623 cites W3106141888 @default.
• W4281708623 cites W3133919270 @default.
• W4281708623 cites W3134765613 @default.
• W4281708623 cites W3145527391 @default.
• W4281708623 cites W3153239684 @default.
• W4281708623 cites W3183011410 @default.
• W4281708623 cites W3207610089 @default.
• W4281708623 cites W4250482878 @default.
• W4281708623 doi "https://doi.org/10.1155/2022/1764606" @default.
• W4281708623 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35685139" @default.
• W4281708623 hasPublicationYear "2022" @default.
• W4281708623 type Work @default.
• W4281708623 citedByCount "0" @default.
• W4281708623 crossrefType "journal-article" @default.
• W4281708623 hasAuthorship W4281708623A5014462835 @default.
• W4281708623 hasAuthorship W4281708623A5067830832 @default.
• W4281708623 hasAuthorship W4281708623A5070386973 @default.
• W4281708623 hasBestOaLocation W42817086231 @default.
• W4281708623 hasConcept C103278499 @default.
• W4281708623 hasConcept C105795698 @default.
• W4281708623 hasConcept C108583219 @default.
• W4281708623 hasConcept C115961682 @default.
• W4281708623 hasConcept C119857082 @default.
• W4281708623 hasConcept C150899416 @default.
• W4281708623 hasConcept C153180895 @default.
• W4281708623 hasConcept C154945302 @default.
• W4281708623 hasConcept C202444582 @default.
• W4281708623 hasConcept C27158222 @default.
• W4281708623 hasConcept C33923547 @default.
• W4281708623 hasConcept C41008148 @default.
• W4281708623 hasConcept C50644808 @default.
• W4281708623 hasConcept C75294576 @default.
• W4281708623 hasConcept C774472 @default.
• W4281708623 hasConcept C81363708 @default.
• W4281708623 hasConcept C8642999 @default.
• W4281708623 hasConcept C9652623 @default.
• W4281708623 hasConceptScore W4281708623C103278499 @default.
• W4281708623 hasConceptScore W4281708623C105795698 @default.
• W4281708623 hasConceptScore W4281708623C108583219 @default.
• W4281708623 hasConceptScore W4281708623C115961682 @default.
• W4281708623 hasConceptScore W4281708623C119857082 @default.
• W4281708623 hasConceptScore W4281708623C150899416 @default.
• W4281708623 hasConceptScore W4281708623C153180895 @default.
• W4281708623 hasConceptScore W4281708623C154945302 @default.
• W4281708623 hasConceptScore W4281708623C202444582 @default.
• W4281708623 hasConceptScore W4281708623C27158222 @default.
• W4281708623 hasConceptScore W4281708623C33923547 @default.
• W4281708623 hasConceptScore W4281708623C41008148 @default.
• W4281708623 hasConceptScore W4281708623C50644808 @default.

• next