Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090449663> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3090449663 endingPage "102930" @default.
- W3090449663 startingPage "102930" @default.
- W3090449663 abstract "Despite excellent performance in image classification researches, the training of the deep neural networks (DNN) needs a large set of clean data with accurate annotations. The collection of a dataset is easy, but annotating the collected data is difficult on the contrary. There are many image data on the websites, which contain inaccurate annotations, but trainings on these datasets may make networks easier to over-fit noisy data and cause performance degradation. In this work, we propose an improved joint optimization framework for noise correction, which uses the Combination of Mix-up entropy and Kullback-Leibler entropy (CMKL) as the loss function. The new loss function can achieve better fine-tuning results after updating all label annotations. The experimental results on publicly available CIFAR-10 dataset and Clothing1M dataset show superior performance of our approach compared with other state-of-the-art methods." @default.
- W3090449663 created "2020-10-08" @default.
- W3090449663 creator A5025664604 @default.
- W3090449663 creator A5045234445 @default.
- W3090449663 creator A5052441498 @default.
- W3090449663 creator A5055370055 @default.
- W3090449663 creator A5087471242 @default.
- W3090449663 creator A5087971299 @default.
- W3090449663 date "2020-10-01" @default.
- W3090449663 modified "2023-10-17" @default.
- W3090449663 title "An improved noise loss correction algorithm for learning from noisy labels" @default.
- W3090449663 cites W2512382915 @default.
- W3090449663 cites W2553156677 @default.
- W3090449663 cites W2737368067 @default.
- W3090449663 cites W2948606739 @default.
- W3090449663 cites W2981873476 @default.
- W3090449663 cites W4244259635 @default.
- W3090449663 doi "https://doi.org/10.1016/j.jvcir.2020.102930" @default.
- W3090449663 hasPublicationYear "2020" @default.
- W3090449663 type Work @default.
- W3090449663 sameAs 3090449663 @default.
- W3090449663 citedByCount "6" @default.
- W3090449663 countsByYear W30904496632021 @default.
- W3090449663 countsByYear W30904496632022 @default.
- W3090449663 countsByYear W30904496632023 @default.
- W3090449663 crossrefType "journal-article" @default.
- W3090449663 hasAuthorship W3090449663A5025664604 @default.
- W3090449663 hasAuthorship W3090449663A5045234445 @default.
- W3090449663 hasAuthorship W3090449663A5052441498 @default.
- W3090449663 hasAuthorship W3090449663A5055370055 @default.
- W3090449663 hasAuthorship W3090449663A5087471242 @default.
- W3090449663 hasAuthorship W3090449663A5087971299 @default.
- W3090449663 hasConcept C106301342 @default.
- W3090449663 hasConcept C11413529 @default.
- W3090449663 hasConcept C115961682 @default.
- W3090449663 hasConcept C119857082 @default.
- W3090449663 hasConcept C121332964 @default.
- W3090449663 hasConcept C124101348 @default.
- W3090449663 hasConcept C14036430 @default.
- W3090449663 hasConcept C153180895 @default.
- W3090449663 hasConcept C154945302 @default.
- W3090449663 hasConcept C177264268 @default.
- W3090449663 hasConcept C199360897 @default.
- W3090449663 hasConcept C2984842247 @default.
- W3090449663 hasConcept C2988416141 @default.
- W3090449663 hasConcept C41008148 @default.
- W3090449663 hasConcept C50644808 @default.
- W3090449663 hasConcept C51632099 @default.
- W3090449663 hasConcept C62520636 @default.
- W3090449663 hasConcept C78458016 @default.
- W3090449663 hasConcept C86803240 @default.
- W3090449663 hasConcept C99498987 @default.
- W3090449663 hasConceptScore W3090449663C106301342 @default.
- W3090449663 hasConceptScore W3090449663C11413529 @default.
- W3090449663 hasConceptScore W3090449663C115961682 @default.
- W3090449663 hasConceptScore W3090449663C119857082 @default.
- W3090449663 hasConceptScore W3090449663C121332964 @default.
- W3090449663 hasConceptScore W3090449663C124101348 @default.
- W3090449663 hasConceptScore W3090449663C14036430 @default.
- W3090449663 hasConceptScore W3090449663C153180895 @default.
- W3090449663 hasConceptScore W3090449663C154945302 @default.
- W3090449663 hasConceptScore W3090449663C177264268 @default.
- W3090449663 hasConceptScore W3090449663C199360897 @default.
- W3090449663 hasConceptScore W3090449663C2984842247 @default.
- W3090449663 hasConceptScore W3090449663C2988416141 @default.
- W3090449663 hasConceptScore W3090449663C41008148 @default.
- W3090449663 hasConceptScore W3090449663C50644808 @default.
- W3090449663 hasConceptScore W3090449663C51632099 @default.
- W3090449663 hasConceptScore W3090449663C62520636 @default.
- W3090449663 hasConceptScore W3090449663C78458016 @default.
- W3090449663 hasConceptScore W3090449663C86803240 @default.
- W3090449663 hasConceptScore W3090449663C99498987 @default.
- W3090449663 hasFunder F4320321001 @default.
- W3090449663 hasFunder F4320334764 @default.
- W3090449663 hasLocation W30904496631 @default.
- W3090449663 hasOpenAccess W3090449663 @default.
- W3090449663 hasPrimaryLocation W30904496631 @default.
- W3090449663 hasRelatedWork W1984843650 @default.
- W3090449663 hasRelatedWork W2098331493 @default.
- W3090449663 hasRelatedWork W2730433920 @default.
- W3090449663 hasRelatedWork W2893359234 @default.
- W3090449663 hasRelatedWork W2943646750 @default.
- W3090449663 hasRelatedWork W2962761044 @default.
- W3090449663 hasRelatedWork W2963361074 @default.
- W3090449663 hasRelatedWork W3000197790 @default.
- W3090449663 hasRelatedWork W4214706004 @default.
- W3090449663 hasRelatedWork W4236608366 @default.
- W3090449663 hasVolume "72" @default.
- W3090449663 isParatext "false" @default.
- W3090449663 isRetracted "false" @default.
- W3090449663 magId "3090449663" @default.
- W3090449663 workType "article" @default.