FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148239730> ?p ?o ?g. }

• W3148239730 abstract "Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution of data, which leads to generating less diverse samples for each class and makes the encoder only achieve sub-optimal clustering performance. Here, we propose a new unsupervised conditional generation framework, Double Cycle-Consistent Conditional GAN (DC3-GAN), which can generate diverse class-conditioned samples. We enforce the encoder and the generator of GAN to form an encoder-generator pair in addition to the generator-encoder pair, which enables us to avoid the low-diversity generation and the triviality of latent features. We train the encoder-generator pair using real data, which can indirectly estimate the real conditional distribution. Meanwhile, this framework enforces the outputs of the encoder to match the inputs of GAN and the prior noise distribution, which disentangles latent space into two parts: one-hot discrete and continuous latent variables. The former can be directly expressed as clusters and the latter represents remaining unspecified factors. This work demonstrates that enhancing the diversity of unsupervised conditional generated samples can improve the clustering performance. Experiments on different benchmark datasets show that the proposed method outperforms existing generative model-based clustering methods, and also achieves the optimal disentanglement performance." @default.
• W3148239730 created "2021-04-13" @default.
• W3148239730 creator A5040998948 @default.
• W3148239730 creator A5067760326 @default.
• W3148239730 creator A5089100714 @default.
• W3148239730 date "2019-11-13" @default.
• W3148239730 modified "2023-09-27" @default.
• W3148239730 title "Double cycle-consistent generative adversarial network for unsupervised conditional generation." @default.
• W3148239730 cites W1487641199 @default.
• W3148239730 cites W1902027874 @default.
• W3148239730 cites W1973207880 @default.
• W3148239730 cites W2019464758 @default.
• W3148239730 cites W2099471712 @default.
• W3148239730 cites W2112796928 @default.
• W3148239730 cites W2121947440 @default.
• W3148239730 cites W2125389028 @default.
• W3148239730 cites W2127218421 @default.
• W3148239730 cites W2133665775 @default.
• W3148239730 cites W2145094598 @default.
• W3148239730 cites W2163922914 @default.
• W3148239730 cites W2173520492 @default.
• W3148239730 cites W2187089797 @default.
• W3148239730 cites W2202109488 @default.
• W3148239730 cites W2212660284 @default.
• W3148239730 cites W2411541852 @default.
• W3148239730 cites W2412320034 @default.
• W3148239730 cites W2533545350 @default.
• W3148239730 cites W2548275288 @default.
• W3148239730 cites W2556467266 @default.
• W3148239730 cites W2559823555 @default.
• W3148239730 cites W2608862709 @default.
• W3148239730 cites W2741943936 @default.
• W3148239730 cites W2750384547 @default.
• W3148239730 cites W2753738274 @default.
• W3148239730 cites W2767757834 @default.
• W3148239730 cites W2779692282 @default.
• W3148239730 cites W2781711557 @default.
• W3148239730 cites W2785519580 @default.
• W3148239730 cites W2788552663 @default.
• W3148239730 cites W2799121188 @default.
• W3148239730 cites W2801365175 @default.
• W3148239730 cites W2805530975 @default.
• W3148239730 cites W2883725317 @default.
• W3148239730 cites W2904849495 @default.
• W3148239730 cites W2906298613 @default.
• W3148239730 cites W2927928207 @default.
• W3148239730 cites W2950365520 @default.
• W3148239730 cites W2951004968 @default.
• W3148239730 cites W2951506174 @default.
• W3148239730 cites W2952074843 @default.
• W3148239730 cites W2952808567 @default.
• W3148239730 cites W2953791858 @default.
• W3148239730 cites W2962852342 @default.
• W3148239730 cites W2962879692 @default.
• W3148239730 cites W2963041308 @default.
• W3148239730 cites W2963113011 @default.
• W3148239730 cites W2963226019 @default.
• W3148239730 cites W2963306805 @default.
• W3148239730 cites W2963549223 @default.
• W3148239730 cites W2963761396 @default.
• W3148239730 cites W2963981733 @default.
• W3148239730 cites W2964074409 @default.
• W3148239730 cites W2964127395 @default.
• W3148239730 cites W2970475648 @default.
• W3148239730 cites W2977167937 @default.
• W3148239730 cites W2986405467 @default.
• W3148239730 cites W2990500698 @default.
• W3148239730 cites W3005680577 @default.
• W3148239730 cites W3035574324 @default.
• W3148239730 cites W3104876213 @default.
• W3148239730 cites W3106709020 @default.
• W3148239730 cites W3117876796 @default.
• W3148239730 cites W3118608800 @default.
• W3148239730 hasPublicationYear "2019" @default.
• W3148239730 type Work @default.
• W3148239730 sameAs 3148239730 @default.
• W3148239730 citedByCount "2" @default.
• W3148239730 countsByYear W31482397302020 @default.
• W3148239730 countsByYear W31482397302021 @default.
• W3148239730 crossrefType "posted-content" @default.
• W3148239730 hasAuthorship W3148239730A5040998948 @default.
• W3148239730 hasAuthorship W3148239730A5067760326 @default.
• W3148239730 hasAuthorship W3148239730A5089100714 @default.
• W3148239730 hasConcept C105795698 @default.
• W3148239730 hasConcept C111919701 @default.
• W3148239730 hasConcept C11413529 @default.
• W3148239730 hasConcept C118505674 @default.
• W3148239730 hasConcept C119857082 @default.
• W3148239730 hasConcept C121332964 @default.
• W3148239730 hasConcept C124101348 @default.
• W3148239730 hasConcept C13280743 @default.
• W3148239730 hasConcept C153180895 @default.
• W3148239730 hasConcept C154945302 @default.
• W3148239730 hasConcept C163258240 @default.
• W3148239730 hasConcept C167966045 @default.
• W3148239730 hasConcept C185798385 @default.
• W3148239730 hasConcept C205649164 @default.
• W3148239730 hasConcept C2779803651 @default.
• W3148239730 hasConcept C2780992000 @default.
• W3148239730 hasConcept C33923547 @default.

• next