Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897636275> ?p ?o ?g. }
- W2897636275 endingPage "547" @default.
- W2897636275 startingPage "539" @default.
- W2897636275 abstract "The improved generative adversarial network (improved GAN) is a successful method using a generative adversarial model to solve the problem of semi-supervised learning (SSL). The improved GAN learns a generator with the technique of mean feature matching which penalizes the discrepancy of the first-order moment of the latent features. To better describe common attributes of a distribution, this paper proposes a novel SSL method which incorporates the first-order and the secondorder moments of the features in an intermediate layer of the discriminator, called mean and variance feature matching GAN (MVFM-GAN). To capture more precisely the data manifold, not only the mean but also the variance is used in the latent feature learning. Compared with improved GAN and other traditional methods, MVFM-GAN achieves superior performance in semi-supervised classification tasks and a better stability of GAN training, particularly in the cases when the number of labeled samples is low. It shows a comparable performance with the state-of-the-art methods on several benchmark data sets. As a byproduct of the novel approach, MVFM-GAN generates realistic images of good visual quality." @default.
- W2897636275 created "2018-10-26" @default.
- W2897636275 creator A5028209738 @default.
- W2897636275 creator A5055922843 @default.
- W2897636275 creator A5087450445 @default.
- W2897636275 date "2019-12-01" @default.
- W2897636275 modified "2023-10-15" @default.
- W2897636275 title "Semi-Supervised Learning Based on GAN With Mean and Variance Feature Matching" @default.
- W2897636275 cites W1832881114 @default.
- W2897636275 cites W1895577753 @default.
- W2897636275 cites W1931639407 @default.
- W2897636275 cites W1973445088 @default.
- W2897636275 cites W2013029619 @default.
- W2897636275 cites W2015229219 @default.
- W2897636275 cites W2048668242 @default.
- W2897636275 cites W2048679005 @default.
- W2897636275 cites W2090159818 @default.
- W2897636275 cites W2157331557 @default.
- W2897636275 cites W2160815625 @default.
- W2897636275 cites W2248620004 @default.
- W2897636275 cites W2342967552 @default.
- W2897636275 cites W2524771588 @default.
- W2897636275 cites W2586404262 @default.
- W2897636275 cites W2620611182 @default.
- W2897636275 cites W2964273402 @default.
- W2897636275 doi "https://doi.org/10.1109/tcds.2018.2875462" @default.
- W2897636275 hasPublicationYear "2019" @default.
- W2897636275 type Work @default.
- W2897636275 sameAs 2897636275 @default.
- W2897636275 citedByCount "11" @default.
- W2897636275 countsByYear W28976362752019 @default.
- W2897636275 countsByYear W28976362752020 @default.
- W2897636275 countsByYear W28976362752021 @default.
- W2897636275 countsByYear W28976362752022 @default.
- W2897636275 countsByYear W28976362752023 @default.
- W2897636275 crossrefType "journal-article" @default.
- W2897636275 hasAuthorship W2897636275A5028209738 @default.
- W2897636275 hasAuthorship W2897636275A5055922843 @default.
- W2897636275 hasAuthorship W2897636275A5087450445 @default.
- W2897636275 hasConcept C105795698 @default.
- W2897636275 hasConcept C112972136 @default.
- W2897636275 hasConcept C119857082 @default.
- W2897636275 hasConcept C121332964 @default.
- W2897636275 hasConcept C121955636 @default.
- W2897636275 hasConcept C13280743 @default.
- W2897636275 hasConcept C138885662 @default.
- W2897636275 hasConcept C144133560 @default.
- W2897636275 hasConcept C153180895 @default.
- W2897636275 hasConcept C154945302 @default.
- W2897636275 hasConcept C165064840 @default.
- W2897636275 hasConcept C179254644 @default.
- W2897636275 hasConcept C185798385 @default.
- W2897636275 hasConcept C196083921 @default.
- W2897636275 hasConcept C205649164 @default.
- W2897636275 hasConcept C2776401178 @default.
- W2897636275 hasConcept C2779803651 @default.
- W2897636275 hasConcept C33923547 @default.
- W2897636275 hasConcept C39890363 @default.
- W2897636275 hasConcept C41008148 @default.
- W2897636275 hasConcept C41895202 @default.
- W2897636275 hasConcept C74650414 @default.
- W2897636275 hasConcept C76155785 @default.
- W2897636275 hasConcept C94915269 @default.
- W2897636275 hasConceptScore W2897636275C105795698 @default.
- W2897636275 hasConceptScore W2897636275C112972136 @default.
- W2897636275 hasConceptScore W2897636275C119857082 @default.
- W2897636275 hasConceptScore W2897636275C121332964 @default.
- W2897636275 hasConceptScore W2897636275C121955636 @default.
- W2897636275 hasConceptScore W2897636275C13280743 @default.
- W2897636275 hasConceptScore W2897636275C138885662 @default.
- W2897636275 hasConceptScore W2897636275C144133560 @default.
- W2897636275 hasConceptScore W2897636275C153180895 @default.
- W2897636275 hasConceptScore W2897636275C154945302 @default.
- W2897636275 hasConceptScore W2897636275C165064840 @default.
- W2897636275 hasConceptScore W2897636275C179254644 @default.
- W2897636275 hasConceptScore W2897636275C185798385 @default.
- W2897636275 hasConceptScore W2897636275C196083921 @default.
- W2897636275 hasConceptScore W2897636275C205649164 @default.
- W2897636275 hasConceptScore W2897636275C2776401178 @default.
- W2897636275 hasConceptScore W2897636275C2779803651 @default.
- W2897636275 hasConceptScore W2897636275C33923547 @default.
- W2897636275 hasConceptScore W2897636275C39890363 @default.
- W2897636275 hasConceptScore W2897636275C41008148 @default.
- W2897636275 hasConceptScore W2897636275C41895202 @default.
- W2897636275 hasConceptScore W2897636275C74650414 @default.
- W2897636275 hasConceptScore W2897636275C76155785 @default.
- W2897636275 hasConceptScore W2897636275C94915269 @default.
- W2897636275 hasFunder F4320321001 @default.
- W2897636275 hasIssue "4" @default.
- W2897636275 hasLocation W28976362751 @default.
- W2897636275 hasOpenAccess W2897636275 @default.
- W2897636275 hasPrimaryLocation W28976362751 @default.
- W2897636275 hasRelatedWork W2382607599 @default.
- W2897636275 hasRelatedWork W2546942002 @default.
- W2897636275 hasRelatedWork W2786306966 @default.
- W2897636275 hasRelatedWork W2886721024 @default.
- W2897636275 hasRelatedWork W2906643110 @default.
- W2897636275 hasRelatedWork W2951337574 @default.