Matches in SemOpenAlex for { <https://semopenalex.org/work/W2396790570> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2396790570 abstract "Deep convolutional neural networks require a huge amount of data samples to train efficient networks. Although many benchmarks manage to create abundant samples to be used for training, they lack efficiency when trying to train convolutional neural networks up to their full potential. The data augmentation is one of the solutions to this problem, but it does not consider the quality of samples, i.e. whether the augmented samples are actually suitable for training or not. In this paper, we propose a method that will allow us to select effective samples from an augmented sample set. The achievements of our method were 1) to be able to generate a large amount of augmented samples from images with labeled data and multiple background images; and 2) to be able to select effective samples from the additionally augmented ones through iterations of parameter updating during the training process. We utilized exhaustless sample generation and effective sample selection in order to perform recognition and segmentation tasks. It obtained the best performance in both tasks when compared to other methods using, or not, sample generation and/or selection." @default.
- W2396790570 created "2016-06-24" @default.
- W2396790570 creator A5011810133 @default.
- W2396790570 creator A5025090520 @default.
- W2396790570 creator A5029132443 @default.
- W2396790570 creator A5062009349 @default.
- W2396790570 date "2015-01-01" @default.
- W2396790570 modified "2023-09-25" @default.
- W2396790570 title "Improving Quality of Training Samples Through Exhaustless Generation and Effective Selection for Deep Convolutional Neural Networks" @default.
- W2396790570 cites W107408668 @default.
- W2396790570 cites W1483336436 @default.
- W2396790570 cites W1487583988 @default.
- W2396790570 cites W1523493493 @default.
- W2396790570 cites W1904365287 @default.
- W2396790570 cites W2056695679 @default.
- W2396790570 cites W2090042335 @default.
- W2396790570 cites W2112796928 @default.
- W2396790570 cites W2116360511 @default.
- W2396790570 cites W2129981175 @default.
- W2396790570 cites W2152945944 @default.
- W2396790570 cites W2156163116 @default.
- W2396790570 cites W2156547346 @default.
- W2396790570 cites W2163605009 @default.
- W2396790570 cites W2175582831 @default.
- W2396790570 cites W2616465717 @default.
- W2396790570 cites W2673062467 @default.
- W2396790570 cites W2766736793 @default.
- W2396790570 cites W2952186574 @default.
- W2396790570 cites W2962820688 @default.
- W2396790570 cites W3037950864 @default.
- W2396790570 cites W4919037 @default.
- W2396790570 doi "https://doi.org/10.5220/0005263802280235" @default.
- W2396790570 hasPublicationYear "2015" @default.
- W2396790570 type Work @default.
- W2396790570 sameAs 2396790570 @default.
- W2396790570 citedByCount "5" @default.
- W2396790570 countsByYear W23967905702019 @default.
- W2396790570 countsByYear W23967905702020 @default.
- W2396790570 countsByYear W23967905702022 @default.
- W2396790570 crossrefType "proceedings-article" @default.
- W2396790570 hasAuthorship W2396790570A5011810133 @default.
- W2396790570 hasAuthorship W2396790570A5025090520 @default.
- W2396790570 hasAuthorship W2396790570A5029132443 @default.
- W2396790570 hasAuthorship W2396790570A5062009349 @default.
- W2396790570 hasConcept C108583219 @default.
- W2396790570 hasConcept C111919701 @default.
- W2396790570 hasConcept C119857082 @default.
- W2396790570 hasConcept C124101348 @default.
- W2396790570 hasConcept C153180895 @default.
- W2396790570 hasConcept C154945302 @default.
- W2396790570 hasConcept C177264268 @default.
- W2396790570 hasConcept C185592680 @default.
- W2396790570 hasConcept C198531522 @default.
- W2396790570 hasConcept C199360897 @default.
- W2396790570 hasConcept C41008148 @default.
- W2396790570 hasConcept C43617362 @default.
- W2396790570 hasConcept C50644808 @default.
- W2396790570 hasConcept C51632099 @default.
- W2396790570 hasConcept C81363708 @default.
- W2396790570 hasConcept C81917197 @default.
- W2396790570 hasConcept C89600930 @default.
- W2396790570 hasConcept C98045186 @default.
- W2396790570 hasConceptScore W2396790570C108583219 @default.
- W2396790570 hasConceptScore W2396790570C111919701 @default.
- W2396790570 hasConceptScore W2396790570C119857082 @default.
- W2396790570 hasConceptScore W2396790570C124101348 @default.
- W2396790570 hasConceptScore W2396790570C153180895 @default.
- W2396790570 hasConceptScore W2396790570C154945302 @default.
- W2396790570 hasConceptScore W2396790570C177264268 @default.
- W2396790570 hasConceptScore W2396790570C185592680 @default.
- W2396790570 hasConceptScore W2396790570C198531522 @default.
- W2396790570 hasConceptScore W2396790570C199360897 @default.
- W2396790570 hasConceptScore W2396790570C41008148 @default.
- W2396790570 hasConceptScore W2396790570C43617362 @default.
- W2396790570 hasConceptScore W2396790570C50644808 @default.
- W2396790570 hasConceptScore W2396790570C51632099 @default.
- W2396790570 hasConceptScore W2396790570C81363708 @default.
- W2396790570 hasConceptScore W2396790570C81917197 @default.
- W2396790570 hasConceptScore W2396790570C89600930 @default.
- W2396790570 hasConceptScore W2396790570C98045186 @default.
- W2396790570 hasLocation W23967905701 @default.
- W2396790570 hasOpenAccess W2396790570 @default.
- W2396790570 hasPrimaryLocation W23967905701 @default.
- W2396790570 hasRelatedWork W2342591535 @default.
- W2396790570 hasRelatedWork W2415731916 @default.
- W2396790570 hasRelatedWork W2744043610 @default.
- W2396790570 hasRelatedWork W2762006829 @default.
- W2396790570 hasRelatedWork W2795329967 @default.
- W2396790570 hasRelatedWork W2901422868 @default.
- W2396790570 hasRelatedWork W3095523211 @default.
- W2396790570 hasRelatedWork W3102253946 @default.
- W2396790570 hasRelatedWork W3121324630 @default.
- W2396790570 hasRelatedWork W3144574764 @default.
- W2396790570 isParatext "false" @default.
- W2396790570 isRetracted "false" @default.
- W2396790570 magId "2396790570" @default.
- W2396790570 workType "article" @default.