Matches in SemOpenAlex for { <https://semopenalex.org/work/W2553156677> ?p ?o ?g. }
- W2553156677 endingPage "2838" @default.
- W2553156677 startingPage "2825" @default.
- W2553156677 abstract "Convolutional Neural Networks (ConvNets) have achieved excellent recognition performance in various visual recognition tasks. A large labeled training set is one of the most important factors for its success. However, it is difficult to collect sufficient training images with precise labels in some domains such as apparent age estimation, head pose estimation, multi-label classification and semantic segmentation. Fortunately, there is ambiguous information among labels, which makes these tasks different from traditional classification. Based on this observation, we convert the label of each image into a discrete label distribution, and learn the label distribution by minimizing a Kullback-Leibler divergence between the predicted and ground-truth label distributions using deep ConvNets. The proposed DLDL (Deep Label Distribution Learning) method effectively utilizes the label ambiguity in both feature learning and classifier learning, which help prevent the network from over-fitting even when the training set is small. Experimental results show that the proposed approach produces significantly better results than state-of-the-art methods for age estimation and head pose estimation. At the same time, it also improves recognition performance for multi-label classification and semantic segmentation tasks." @default.
- W2553156677 created "2016-11-30" @default.
- W2553156677 creator A5000290451 @default.
- W2553156677 creator A5015045452 @default.
- W2553156677 creator A5073981884 @default.
- W2553156677 creator A5074742406 @default.
- W2553156677 creator A5090881698 @default.
- W2553156677 date "2017-06-01" @default.
- W2553156677 modified "2023-10-14" @default.
- W2553156677 title "Deep Label Distribution Learning With Label Ambiguity" @default.
- W2553156677 cites W1167806532 @default.
- W2553156677 cites W1475738481 @default.
- W2553156677 cites W1567302070 @default.
- W2553156677 cites W1669690275 @default.
- W2553156677 cites W1677182931 @default.
- W2553156677 cites W1903029394 @default.
- W2553156677 cites W1935588821 @default.
- W2553156677 cites W1963882359 @default.
- W2553156677 cites W1974744233 @default.
- W2553156677 cites W1976948919 @default.
- W2553156677 cites W2010181071 @default.
- W2553156677 cites W2012885984 @default.
- W2553156677 cites W2022566595 @default.
- W2553156677 cites W2031489346 @default.
- W2553156677 cites W2037511607 @default.
- W2553156677 cites W2046554054 @default.
- W2553156677 cites W2066454034 @default.
- W2553156677 cites W2066650804 @default.
- W2553156677 cites W2066808422 @default.
- W2553156677 cites W2088115584 @default.
- W2553156677 cites W2102605133 @default.
- W2553156677 cites W2116626343 @default.
- W2553156677 cites W2118664399 @default.
- W2553156677 cites W2121947440 @default.
- W2553156677 cites W2144794286 @default.
- W2553156677 cites W2161381512 @default.
- W2553156677 cites W2183341477 @default.
- W2553156677 cites W2194775991 @default.
- W2553156677 cites W2239239723 @default.
- W2553156677 cites W2239890062 @default.
- W2553156677 cites W2330485005 @default.
- W2553156677 cites W2442264559 @default.
- W2553156677 cites W2510725918 @default.
- W2553156677 cites W2579021424 @default.
- W2553156677 cites W3125882365 @default.
- W2553156677 cites W610429473 @default.
- W2553156677 doi "https://doi.org/10.1109/tip.2017.2689998" @default.
- W2553156677 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28371776" @default.
- W2553156677 hasPublicationYear "2017" @default.
- W2553156677 type Work @default.
- W2553156677 sameAs 2553156677 @default.
- W2553156677 citedByCount "278" @default.
- W2553156677 countsByYear W25531566772016 @default.
- W2553156677 countsByYear W25531566772017 @default.
- W2553156677 countsByYear W25531566772018 @default.
- W2553156677 countsByYear W25531566772019 @default.
- W2553156677 countsByYear W25531566772020 @default.
- W2553156677 countsByYear W25531566772021 @default.
- W2553156677 countsByYear W25531566772022 @default.
- W2553156677 countsByYear W25531566772023 @default.
- W2553156677 crossrefType "journal-article" @default.
- W2553156677 hasAuthorship W2553156677A5000290451 @default.
- W2553156677 hasAuthorship W2553156677A5015045452 @default.
- W2553156677 hasAuthorship W2553156677A5073981884 @default.
- W2553156677 hasAuthorship W2553156677A5074742406 @default.
- W2553156677 hasAuthorship W2553156677A5090881698 @default.
- W2553156677 hasBestOaLocation W25531566772 @default.
- W2553156677 hasConcept C108583219 @default.
- W2553156677 hasConcept C115961682 @default.
- W2553156677 hasConcept C119857082 @default.
- W2553156677 hasConcept C124504099 @default.
- W2553156677 hasConcept C138885662 @default.
- W2553156677 hasConcept C146849305 @default.
- W2553156677 hasConcept C153180895 @default.
- W2553156677 hasConcept C154945302 @default.
- W2553156677 hasConcept C199360897 @default.
- W2553156677 hasConcept C2776401178 @default.
- W2553156677 hasConcept C2776482837 @default.
- W2553156677 hasConcept C2780522230 @default.
- W2553156677 hasConcept C41008148 @default.
- W2553156677 hasConcept C41895202 @default.
- W2553156677 hasConcept C50644808 @default.
- W2553156677 hasConcept C52622490 @default.
- W2553156677 hasConcept C75294576 @default.
- W2553156677 hasConcept C81363708 @default.
- W2553156677 hasConcept C89600930 @default.
- W2553156677 hasConcept C95623464 @default.
- W2553156677 hasConceptScore W2553156677C108583219 @default.
- W2553156677 hasConceptScore W2553156677C115961682 @default.
- W2553156677 hasConceptScore W2553156677C119857082 @default.
- W2553156677 hasConceptScore W2553156677C124504099 @default.
- W2553156677 hasConceptScore W2553156677C138885662 @default.
- W2553156677 hasConceptScore W2553156677C146849305 @default.
- W2553156677 hasConceptScore W2553156677C153180895 @default.
- W2553156677 hasConceptScore W2553156677C154945302 @default.
- W2553156677 hasConceptScore W2553156677C199360897 @default.
- W2553156677 hasConceptScore W2553156677C2776401178 @default.
- W2553156677 hasConceptScore W2553156677C2776482837 @default.