Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049327567> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3049327567 abstract "Generative adversarial networks (GANs) are potential models in semi-supervised learning because of the excellent performance of GANs. However, most GAN-based semi-supervised models are sensitive to local perturbation, which means those models are not stable enough. Besides, Softmax classifier is the first choice of those models. In this paper, a novel method is proposed by introducing a discriminator using scalable SVM classifier with manifold regularization. Scalable SVM classifiers typically perform better in small sample data sets compared with other classifiers, which is consistent with the feature that semi-supervised learning consists of a few labeled data and a large number of unlabeled data. Manifold regularization forces discriminator to keep invariable to local perturbations. By incorporating into feature-matching GAN architecture, the proposed GANs-based semi-supervised learning algorithm has advantages over other methods on the Cifar-10, SVHN and Cifar-100 datasets. The results show that the proposed model SSVM-GAN has good robustness and strong generalization ability." @default.
- W3049327567 created "2020-08-21" @default.
- W3049327567 creator A5001215846 @default.
- W3049327567 creator A5008541218 @default.
- W3049327567 creator A5054199668 @default.
- W3049327567 creator A5056726197 @default.
- W3049327567 creator A5066176083 @default.
- W3049327567 date "2020-08-01" @default.
- W3049327567 modified "2023-09-27" @default.
- W3049327567 title "Semi-supervised Generative Adversarial Networks Based on Scalable Support Vector Machines and Manifold Regularization" @default.
- W3049327567 cites W1546411676 @default.
- W3049327567 cites W1710476689 @default.
- W3049327567 cites W1836465849 @default.
- W3049327567 cites W2048679005 @default.
- W3049327567 cites W2104290444 @default.
- W3049327567 cites W2107968230 @default.
- W3049327567 cites W2134284153 @default.
- W3049327567 cites W2178768799 @default.
- W3049327567 cites W2860944174 @default.
- W3049327567 cites W2963373786 @default.
- W3049327567 cites W2964159205 @default.
- W3049327567 cites W2964218010 @default.
- W3049327567 doi "https://doi.org/10.1109/ccdc49329.2020.9164865" @default.
- W3049327567 hasPublicationYear "2020" @default.
- W3049327567 type Work @default.
- W3049327567 sameAs 3049327567 @default.
- W3049327567 citedByCount "1" @default.
- W3049327567 countsByYear W30493275672022 @default.
- W3049327567 crossrefType "proceedings-article" @default.
- W3049327567 hasAuthorship W3049327567A5001215846 @default.
- W3049327567 hasAuthorship W3049327567A5008541218 @default.
- W3049327567 hasAuthorship W3049327567A5054199668 @default.
- W3049327567 hasAuthorship W3049327567A5056726197 @default.
- W3049327567 hasAuthorship W3049327567A5066176083 @default.
- W3049327567 hasConcept C119857082 @default.
- W3049327567 hasConcept C12267149 @default.
- W3049327567 hasConcept C136389625 @default.
- W3049327567 hasConcept C153180895 @default.
- W3049327567 hasConcept C154945302 @default.
- W3049327567 hasConcept C188441871 @default.
- W3049327567 hasConcept C2776135515 @default.
- W3049327567 hasConcept C2776145971 @default.
- W3049327567 hasConcept C2779803651 @default.
- W3049327567 hasConcept C41008148 @default.
- W3049327567 hasConcept C48044578 @default.
- W3049327567 hasConcept C50644808 @default.
- W3049327567 hasConcept C58973888 @default.
- W3049327567 hasConcept C76155785 @default.
- W3049327567 hasConcept C77088390 @default.
- W3049327567 hasConcept C94915269 @default.
- W3049327567 hasConcept C95623464 @default.
- W3049327567 hasConceptScore W3049327567C119857082 @default.
- W3049327567 hasConceptScore W3049327567C12267149 @default.
- W3049327567 hasConceptScore W3049327567C136389625 @default.
- W3049327567 hasConceptScore W3049327567C153180895 @default.
- W3049327567 hasConceptScore W3049327567C154945302 @default.
- W3049327567 hasConceptScore W3049327567C188441871 @default.
- W3049327567 hasConceptScore W3049327567C2776135515 @default.
- W3049327567 hasConceptScore W3049327567C2776145971 @default.
- W3049327567 hasConceptScore W3049327567C2779803651 @default.
- W3049327567 hasConceptScore W3049327567C41008148 @default.
- W3049327567 hasConceptScore W3049327567C48044578 @default.
- W3049327567 hasConceptScore W3049327567C50644808 @default.
- W3049327567 hasConceptScore W3049327567C58973888 @default.
- W3049327567 hasConceptScore W3049327567C76155785 @default.
- W3049327567 hasConceptScore W3049327567C77088390 @default.
- W3049327567 hasConceptScore W3049327567C94915269 @default.
- W3049327567 hasConceptScore W3049327567C95623464 @default.
- W3049327567 hasLocation W30493275671 @default.
- W3049327567 hasOpenAccess W3049327567 @default.
- W3049327567 hasPrimaryLocation W30493275671 @default.
- W3049327567 hasRelatedWork W1542934499 @default.
- W3049327567 hasRelatedWork W2989610201 @default.
- W3049327567 hasRelatedWork W3120994036 @default.
- W3049327567 hasRelatedWork W3175849793 @default.
- W3049327567 hasRelatedWork W3181161034 @default.
- W3049327567 hasRelatedWork W3204638265 @default.
- W3049327567 hasRelatedWork W4287394940 @default.
- W3049327567 hasRelatedWork W4293496215 @default.
- W3049327567 hasRelatedWork W4294974824 @default.
- W3049327567 hasRelatedWork W98693656 @default.
- W3049327567 isParatext "false" @default.
- W3049327567 isRetracted "false" @default.
- W3049327567 magId "3049327567" @default.
- W3049327567 workType "article" @default.