Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892456951> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2892456951 endingPage "103" @default.
- W2892456951 startingPage "95" @default.
- W2892456951 abstract "Data augmentation is a popular technique largely used to enhance the training of convolutional neural networks. Although many of its benefits are well known by deep learning researchers and practitioners, its implicit regularization effects, as compared to popular explicit regularization techniques, such as weight decay and dropout, remain largely unstudied. As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary. In this paper, we systematically analyze these techniques through ablation studies of different network architectures trained with different amounts of training data. Our results unveil a largely ignored advantage of data augmentation: networks trained with just data augmentation more easily adapt to different architectures and amount of training data, as opposed to weight decay and dropout, which require specific fine-tuning of their hyperparameters." @default.
- W2892456951 created "2018-10-05" @default.
- W2892456951 creator A5024328042 @default.
- W2892456951 creator A5074140704 @default.
- W2892456951 date "2018-01-01" @default.
- W2892456951 modified "2023-10-16" @default.
- W2892456951 title "Further Advantages of Data Augmentation on Convolutional Neural Networks" @default.
- W2892456951 cites W1677182931 @default.
- W2892456951 cites W2130858665 @default.
- W2892456951 cites W2132424367 @default.
- W2892456951 cites W2194775991 @default.
- W2892456951 cites W2604262106 @default.
- W2892456951 cites W2669032454 @default.
- W2892456951 cites W2894737833 @default.
- W2892456951 cites W2912916193 @default.
- W2892456951 cites W2919115771 @default.
- W2892456951 cites W2964137095 @default.
- W2892456951 cites W4238284510 @default.
- W2892456951 doi "https://doi.org/10.1007/978-3-030-01418-6_10" @default.
- W2892456951 hasPublicationYear "2018" @default.
- W2892456951 type Work @default.
- W2892456951 sameAs 2892456951 @default.
- W2892456951 citedByCount "34" @default.
- W2892456951 countsByYear W28924569512020 @default.
- W2892456951 countsByYear W28924569512021 @default.
- W2892456951 countsByYear W28924569512022 @default.
- W2892456951 countsByYear W28924569512023 @default.
- W2892456951 crossrefType "book-chapter" @default.
- W2892456951 hasAuthorship W2892456951A5024328042 @default.
- W2892456951 hasAuthorship W2892456951A5074140704 @default.
- W2892456951 hasBestOaLocation W28924569512 @default.
- W2892456951 hasConcept C108583219 @default.
- W2892456951 hasConcept C119857082 @default.
- W2892456951 hasConcept C153180895 @default.
- W2892456951 hasConcept C154945302 @default.
- W2892456951 hasConcept C2776135515 @default.
- W2892456951 hasConcept C2776145597 @default.
- W2892456951 hasConcept C2984842247 @default.
- W2892456951 hasConcept C41008148 @default.
- W2892456951 hasConcept C50644808 @default.
- W2892456951 hasConcept C51632099 @default.
- W2892456951 hasConcept C81363708 @default.
- W2892456951 hasConcept C8642999 @default.
- W2892456951 hasConceptScore W2892456951C108583219 @default.
- W2892456951 hasConceptScore W2892456951C119857082 @default.
- W2892456951 hasConceptScore W2892456951C153180895 @default.
- W2892456951 hasConceptScore W2892456951C154945302 @default.
- W2892456951 hasConceptScore W2892456951C2776135515 @default.
- W2892456951 hasConceptScore W2892456951C2776145597 @default.
- W2892456951 hasConceptScore W2892456951C2984842247 @default.
- W2892456951 hasConceptScore W2892456951C41008148 @default.
- W2892456951 hasConceptScore W2892456951C50644808 @default.
- W2892456951 hasConceptScore W2892456951C51632099 @default.
- W2892456951 hasConceptScore W2892456951C81363708 @default.
- W2892456951 hasConceptScore W2892456951C8642999 @default.
- W2892456951 hasLocation W28924569511 @default.
- W2892456951 hasLocation W28924569512 @default.
- W2892456951 hasOpenAccess W2892456951 @default.
- W2892456951 hasPrimaryLocation W28924569511 @default.
- W2892456951 hasRelatedWork W2576264401 @default.
- W2892456951 hasRelatedWork W2732542196 @default.
- W2892456951 hasRelatedWork W2738221750 @default.
- W2892456951 hasRelatedWork W2892456951 @default.
- W2892456951 hasRelatedWork W3130227562 @default.
- W2892456951 hasRelatedWork W3206248117 @default.
- W2892456951 hasRelatedWork W4295309597 @default.
- W2892456951 hasRelatedWork W4304182771 @default.
- W2892456951 hasRelatedWork W4309113015 @default.
- W2892456951 hasRelatedWork W4311257506 @default.
- W2892456951 isParatext "false" @default.
- W2892456951 isRetracted "false" @default.
- W2892456951 magId "2892456951" @default.
- W2892456951 workType "book-chapter" @default.