Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042252233> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3042252233 abstract "In general, sufficient data is essential for the better performance and generalization of deep-learning models. However, lots of limitations(cost, resources, etc.) of data collection leads to lack of enough data in most of the areas. In addition, various domains of each data sources and licenses also lead to difficulties in collection of sufficient data. This situation makes us hard to utilize not only the pre-trained model, but also the external knowledge. Therefore, it is important to leverage small dataset effectively for achieving the better performance. We applied some techniques in three aspects: data, loss function, and prediction to enable training from scratch with less data. With these methods, we obtain high accuracy by leveraging ImageNet data which consist of only 50 images per class. Furthermore, our model is ranked 4th in Visual Inductive Printers for Data-Effective Computer Vision Challenge." @default.
- W3042252233 created "2020-07-23" @default.
- W3042252233 creator A5006418733 @default.
- W3042252233 creator A5039743908 @default.
- W3042252233 creator A5055085199 @default.
- W3042252233 creator A5064407466 @default.
- W3042252233 creator A5067723961 @default.
- W3042252233 date "2020-07-15" @default.
- W3042252233 modified "2023-09-27" @default.
- W3042252233 title "Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble." @default.
- W3042252233 cites W2946948417 @default.
- W3042252233 cites W2963351448 @default.
- W3042252233 cites W2991391304 @default.
- W3042252233 cites W3010290582 @default.
- W3042252233 cites W3035003500 @default.
- W3042252233 cites W3035682985 @default.
- W3042252233 hasPublicationYear "2020" @default.
- W3042252233 type Work @default.
- W3042252233 sameAs 3042252233 @default.
- W3042252233 citedByCount "1" @default.
- W3042252233 countsByYear W30422522332021 @default.
- W3042252233 crossrefType "posted-content" @default.
- W3042252233 hasAuthorship W3042252233A5006418733 @default.
- W3042252233 hasAuthorship W3042252233A5039743908 @default.
- W3042252233 hasAuthorship W3042252233A5055085199 @default.
- W3042252233 hasAuthorship W3042252233A5064407466 @default.
- W3042252233 hasAuthorship W3042252233A5067723961 @default.
- W3042252233 hasConcept C105795698 @default.
- W3042252233 hasConcept C108583219 @default.
- W3042252233 hasConcept C111919701 @default.
- W3042252233 hasConcept C119857082 @default.
- W3042252233 hasConcept C124101348 @default.
- W3042252233 hasConcept C133462117 @default.
- W3042252233 hasConcept C134306372 @default.
- W3042252233 hasConcept C14036430 @default.
- W3042252233 hasConcept C153083717 @default.
- W3042252233 hasConcept C154945302 @default.
- W3042252233 hasConcept C177148314 @default.
- W3042252233 hasConcept C2777212361 @default.
- W3042252233 hasConcept C2781235140 @default.
- W3042252233 hasConcept C33923547 @default.
- W3042252233 hasConcept C41008148 @default.
- W3042252233 hasConcept C51632099 @default.
- W3042252233 hasConcept C78458016 @default.
- W3042252233 hasConcept C86803240 @default.
- W3042252233 hasConceptScore W3042252233C105795698 @default.
- W3042252233 hasConceptScore W3042252233C108583219 @default.
- W3042252233 hasConceptScore W3042252233C111919701 @default.
- W3042252233 hasConceptScore W3042252233C119857082 @default.
- W3042252233 hasConceptScore W3042252233C124101348 @default.
- W3042252233 hasConceptScore W3042252233C133462117 @default.
- W3042252233 hasConceptScore W3042252233C134306372 @default.
- W3042252233 hasConceptScore W3042252233C14036430 @default.
- W3042252233 hasConceptScore W3042252233C153083717 @default.
- W3042252233 hasConceptScore W3042252233C154945302 @default.
- W3042252233 hasConceptScore W3042252233C177148314 @default.
- W3042252233 hasConceptScore W3042252233C2777212361 @default.
- W3042252233 hasConceptScore W3042252233C2781235140 @default.
- W3042252233 hasConceptScore W3042252233C33923547 @default.
- W3042252233 hasConceptScore W3042252233C41008148 @default.
- W3042252233 hasConceptScore W3042252233C51632099 @default.
- W3042252233 hasConceptScore W3042252233C78458016 @default.
- W3042252233 hasConceptScore W3042252233C86803240 @default.
- W3042252233 hasLocation W30422522331 @default.
- W3042252233 hasOpenAccess W3042252233 @default.
- W3042252233 hasPrimaryLocation W30422522331 @default.
- W3042252233 hasRelatedWork W2805533881 @default.
- W3042252233 hasRelatedWork W2898091194 @default.
- W3042252233 hasRelatedWork W2947620140 @default.
- W3042252233 hasRelatedWork W2954732411 @default.
- W3042252233 hasRelatedWork W2972998623 @default.
- W3042252233 hasRelatedWork W2981914352 @default.
- W3042252233 hasRelatedWork W3007351208 @default.
- W3042252233 hasRelatedWork W3013319350 @default.
- W3042252233 hasRelatedWork W3102842959 @default.
- W3042252233 hasRelatedWork W3103889740 @default.
- W3042252233 hasRelatedWork W3104340084 @default.
- W3042252233 hasRelatedWork W3120217354 @default.
- W3042252233 hasRelatedWork W3130848852 @default.
- W3042252233 hasRelatedWork W3135495209 @default.
- W3042252233 hasRelatedWork W3137431396 @default.
- W3042252233 hasRelatedWork W3176245410 @default.
- W3042252233 hasRelatedWork W3188761398 @default.
- W3042252233 hasRelatedWork W3213485676 @default.
- W3042252233 hasRelatedWork W3214594231 @default.
- W3042252233 hasRelatedWork W3087994737 @default.
- W3042252233 isParatext "false" @default.
- W3042252233 isRetracted "false" @default.
- W3042252233 magId "3042252233" @default.
- W3042252233 workType "article" @default.