Matches in SemOpenAlex for { <https://semopenalex.org/work/W2923959858> ?p ?o ?g. }
- W2923959858 endingPage "176483" @default.
- W2923959858 startingPage "176470" @default.
- W2923959858 abstract "Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly obtain satisfactory performance for the challenging GZSL by adversarial learning the distribution of semantic classes. To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL. TFGNSCS can not only consider the semantic structure relationship between seen and unseen classes, but also learn the difference of generating features by transferring classification model information from seen to unseen classes in networks. The proposed method can integrate the transfer loss, the classification loss and the Wasserstein distance loss to generate enough CNN features, on which softmax classifiers are trained for ZSL and GZSL. Experiments demonstrate that the performance of TFGNSCS outperforms that of the state of the arts on four challenging datasets, which are CUB,FLO,SUN, AWA in GZSL." @default.
- W2923959858 created "2019-04-01" @default.
- W2923959858 creator A5032884063 @default.
- W2923959858 creator A5033113658 @default.
- W2923959858 creator A5076564474 @default.
- W2923959858 creator A5090866370 @default.
- W2923959858 creator A5091592535 @default.
- W2923959858 date "2019-01-01" @default.
- W2923959858 modified "2023-10-15" @default.
- W2923959858 title "Transfer Feature Generating Networks With Semantic Classes Structure for Zero-Shot Learning" @default.
- W2923959858 cites W1992454046 @default.
- W2923959858 cites W2070148066 @default.
- W2923959858 cites W2077071968 @default.
- W2923959858 cites W2128532956 @default.
- W2923959858 cites W2141350700 @default.
- W2923959858 cites W2147901574 @default.
- W2923959858 cites W2171061940 @default.
- W2923959858 cites W2194775991 @default.
- W2923959858 cites W2289084343 @default.
- W2923959858 cites W2298992465 @default.
- W2923959858 cites W2334493732 @default.
- W2923959858 cites W2398118205 @default.
- W2923959858 cites W2405223529 @default.
- W2923959858 cites W2533598788 @default.
- W2923959858 cites W2594524198 @default.
- W2923959858 cites W2611632661 @default.
- W2923959858 cites W2744242754 @default.
- W2923959858 cites W2762085884 @default.
- W2923959858 cites W2799215068 @default.
- W2923959858 cites W2883360306 @default.
- W2923959858 cites W2888198675 @default.
- W2923959858 cites W2891932073 @default.
- W2923959858 cites W2898502605 @default.
- W2923959858 cites W2901194007 @default.
- W2923959858 cites W2904378456 @default.
- W2923959858 cites W2917263522 @default.
- W2923959858 cites W2937534293 @default.
- W2923959858 cites W2962716320 @default.
- W2923959858 cites W2963052338 @default.
- W2923959858 cites W2963163163 @default.
- W2923959858 cites W2963486920 @default.
- W2923959858 cites W2963545832 @default.
- W2923959858 cites W2963955422 @default.
- W2923959858 cites W2963960318 @default.
- W2923959858 cites W2964086552 @default.
- W2923959858 cites W3100093508 @default.
- W2923959858 cites W3105075099 @default.
- W2923959858 doi "https://doi.org/10.1109/access.2019.2958052" @default.
- W2923959858 hasPublicationYear "2019" @default.
- W2923959858 type Work @default.
- W2923959858 sameAs 2923959858 @default.
- W2923959858 citedByCount "3" @default.
- W2923959858 countsByYear W29239598582020 @default.
- W2923959858 countsByYear W29239598582022 @default.
- W2923959858 crossrefType "journal-article" @default.
- W2923959858 hasAuthorship W2923959858A5032884063 @default.
- W2923959858 hasAuthorship W2923959858A5033113658 @default.
- W2923959858 hasAuthorship W2923959858A5076564474 @default.
- W2923959858 hasAuthorship W2923959858A5090866370 @default.
- W2923959858 hasAuthorship W2923959858A5091592535 @default.
- W2923959858 hasBestOaLocation W29239598581 @default.
- W2923959858 hasConcept C119857082 @default.
- W2923959858 hasConcept C134306372 @default.
- W2923959858 hasConcept C138885662 @default.
- W2923959858 hasConcept C150899416 @default.
- W2923959858 hasConcept C153180895 @default.
- W2923959858 hasConcept C154945302 @default.
- W2923959858 hasConcept C177148314 @default.
- W2923959858 hasConcept C188441871 @default.
- W2923959858 hasConcept C19768560 @default.
- W2923959858 hasConcept C199360897 @default.
- W2923959858 hasConcept C2776401178 @default.
- W2923959858 hasConcept C2780801425 @default.
- W2923959858 hasConcept C2780813799 @default.
- W2923959858 hasConcept C2781122975 @default.
- W2923959858 hasConcept C33923547 @default.
- W2923959858 hasConcept C41008148 @default.
- W2923959858 hasConcept C41895202 @default.
- W2923959858 hasConcept C50644808 @default.
- W2923959858 hasConcept C83665646 @default.
- W2923959858 hasConceptScore W2923959858C119857082 @default.
- W2923959858 hasConceptScore W2923959858C134306372 @default.
- W2923959858 hasConceptScore W2923959858C138885662 @default.
- W2923959858 hasConceptScore W2923959858C150899416 @default.
- W2923959858 hasConceptScore W2923959858C153180895 @default.
- W2923959858 hasConceptScore W2923959858C154945302 @default.
- W2923959858 hasConceptScore W2923959858C177148314 @default.
- W2923959858 hasConceptScore W2923959858C188441871 @default.
- W2923959858 hasConceptScore W2923959858C19768560 @default.
- W2923959858 hasConceptScore W2923959858C199360897 @default.
- W2923959858 hasConceptScore W2923959858C2776401178 @default.
- W2923959858 hasConceptScore W2923959858C2780801425 @default.
- W2923959858 hasConceptScore W2923959858C2780813799 @default.
- W2923959858 hasConceptScore W2923959858C2781122975 @default.
- W2923959858 hasConceptScore W2923959858C33923547 @default.
- W2923959858 hasConceptScore W2923959858C41008148 @default.
- W2923959858 hasConceptScore W2923959858C41895202 @default.
- W2923959858 hasConceptScore W2923959858C50644808 @default.