Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200196913> ?p ?o ?g. }
- W4200196913 endingPage "107780" @default.
- W4200196913 startingPage "107780" @default.
- W4200196913 abstract "Zero-Shot Learning (ZSL) aims to employ seen images and their related semantics to identify unseen images through knowledge transfer. Among past numerous methods, the generative methods are more prominent and achieve better results than other methods. However, we find the input for generating samples is too monotonous, there are only semantics of each class and artificially defined noise, which makes the generated visual features non-discriminative and the classifier cannot effectively distinguish them. In order to solve this problem, we propose a novel approach with cascade Generative Adversarial Network (GAN) to generate discriminative and representative features. In this method, we define a latent space where the features from different categories are orthogonal to each other and the generator for this latent space is learned with a Wasserstein GAN. In addition, in order to make up for the deficiency that the features in this latent space cannot accurately simulate the true distribution of species, we utilize another Wasserstein GAN or Cramér GAN cascaded with the previous one to generate more discriminative and representative visual features. In this way, we can not only expand the content used as input in the generation process, but also make the final generated visual features clear and separable under the influence of latent spatial orthogonality. Extensive experiments on five benchmark datasets, i.e., AWA1, AWA2, CUB, SUN and APY, demonstrate that our proposed method can outperform most of the state-of-the-art methods on both conventional and generalized zero-shot learning settings." @default.
- W4200196913 created "2021-12-31" @default.
- W4200196913 creator A5006276577 @default.
- W4200196913 creator A5016247312 @default.
- W4200196913 creator A5039671101 @default.
- W4200196913 creator A5063481044 @default.
- W4200196913 creator A5064008061 @default.
- W4200196913 creator A5087729203 @default.
- W4200196913 date "2022-01-01" @default.
- W4200196913 modified "2023-10-16" @default.
- W4200196913 title "Learning discriminative and representative feature with cascade GAN for generalized zero-shot learning" @default.
- W4200196913 cites W2109317801 @default.
- W4200196913 cites W2128532956 @default.
- W4200196913 cites W2289084343 @default.
- W4200196913 cites W2476238768 @default.
- W4200196913 cites W2611632661 @default.
- W4200196913 cites W2799215068 @default.
- W4200196913 cites W2805087257 @default.
- W4200196913 cites W2864476761 @default.
- W4200196913 cites W2887567284 @default.
- W4200196913 cites W2891932073 @default.
- W4200196913 cites W2901734189 @default.
- W4200196913 cites W2924476266 @default.
- W4200196913 cites W2944466654 @default.
- W4200196913 cites W2946319046 @default.
- W4200196913 cites W2948162522 @default.
- W4200196913 cites W2962689421 @default.
- W4200196913 cites W2962785568 @default.
- W4200196913 cites W2962791511 @default.
- W4200196913 cites W2963163163 @default.
- W4200196913 cites W2963283377 @default.
- W4200196913 cites W2963499153 @default.
- W4200196913 cites W2963955422 @default.
- W4200196913 cites W2963960318 @default.
- W4200196913 cites W2964086552 @default.
- W4200196913 cites W2964105864 @default.
- W4200196913 cites W2964248207 @default.
- W4200196913 cites W2978762605 @default.
- W4200196913 cites W2979402357 @default.
- W4200196913 cites W2979571231 @default.
- W4200196913 cites W2990947836 @default.
- W4200196913 cites W2991221721 @default.
- W4200196913 cites W2998708909 @default.
- W4200196913 cites W3002728158 @default.
- W4200196913 cites W3013898374 @default.
- W4200196913 cites W3015843040 @default.
- W4200196913 cites W3015970443 @default.
- W4200196913 cites W3016694232 @default.
- W4200196913 cites W3034359780 @default.
- W4200196913 cites W3034379915 @default.
- W4200196913 cites W3035297600 @default.
- W4200196913 cites W3035655772 @default.
- W4200196913 cites W3046428525 @default.
- W4200196913 cites W3048071331 @default.
- W4200196913 cites W3100093508 @default.
- W4200196913 cites W3119712289 @default.
- W4200196913 cites W3120425290 @default.
- W4200196913 cites W3203055845 @default.
- W4200196913 doi "https://doi.org/10.1016/j.knosys.2021.107780" @default.
- W4200196913 hasPublicationYear "2022" @default.
- W4200196913 type Work @default.
- W4200196913 citedByCount "5" @default.
- W4200196913 countsByYear W42001969132022 @default.
- W4200196913 countsByYear W42001969132023 @default.
- W4200196913 crossrefType "journal-article" @default.
- W4200196913 hasAuthorship W4200196913A5006276577 @default.
- W4200196913 hasAuthorship W4200196913A5016247312 @default.
- W4200196913 hasAuthorship W4200196913A5039671101 @default.
- W4200196913 hasAuthorship W4200196913A5063481044 @default.
- W4200196913 hasAuthorship W4200196913A5064008061 @default.
- W4200196913 hasAuthorship W4200196913A5087729203 @default.
- W4200196913 hasConcept C119857082 @default.
- W4200196913 hasConcept C153180895 @default.
- W4200196913 hasConcept C154945302 @default.
- W4200196913 hasConcept C185592680 @default.
- W4200196913 hasConcept C34146451 @default.
- W4200196913 hasConcept C41008148 @default.
- W4200196913 hasConcept C43617362 @default.
- W4200196913 hasConcept C83665646 @default.
- W4200196913 hasConcept C95623464 @default.
- W4200196913 hasConcept C97931131 @default.
- W4200196913 hasConceptScore W4200196913C119857082 @default.
- W4200196913 hasConceptScore W4200196913C153180895 @default.
- W4200196913 hasConceptScore W4200196913C154945302 @default.
- W4200196913 hasConceptScore W4200196913C185592680 @default.
- W4200196913 hasConceptScore W4200196913C34146451 @default.
- W4200196913 hasConceptScore W4200196913C41008148 @default.
- W4200196913 hasConceptScore W4200196913C43617362 @default.
- W4200196913 hasConceptScore W4200196913C83665646 @default.
- W4200196913 hasConceptScore W4200196913C95623464 @default.
- W4200196913 hasConceptScore W4200196913C97931131 @default.
- W4200196913 hasFunder F4320321001 @default.
- W4200196913 hasFunder F4320322769 @default.
- W4200196913 hasLocation W42001969131 @default.
- W4200196913 hasOpenAccess W4200196913 @default.
- W4200196913 hasPrimaryLocation W42001969131 @default.
- W4200196913 hasRelatedWork W1461621550 @default.
- W4200196913 hasRelatedWork W1967062067 @default.