FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952006246> ?p ?o ?g. }

• W2952006246 abstract "Clustering is among the most fundamental tasks in computer vision and machine learning. In this paper, we propose Variational Deep Embedding (VaDE), a novel unsupervised generative clustering approach within the framework of Variational Auto-Encoder (VAE). Specifically, VaDE models the data generative procedure with a Gaussian Mixture Model (GMM) and a deep neural network (DNN): 1) the GMM picks a cluster; 2) from which a latent embedding is generated; 3) then the DNN decodes the latent embedding into observables. Inference in VaDE is done in a variational way: a different DNN is used to encode observables to latent embeddings, so that the evidence lower bound (ELBO) can be optimized using Stochastic Gradient Variational Bayes (SGVB) estimator and the reparameterization trick. Quantitative comparisons with strong baselines are included in this paper, and experimental results show that VaDE significantly outperforms the state-of-the-art clustering methods on 4 benchmarks from various modalities. Moreover, by VaDE's generative nature, we show its capability of generating highly realistic samples for any specified cluster, without using supervised information during training. Lastly, VaDE is a flexible and extensible framework for unsupervised generative clustering, more general mixture models than GMM can be easily plugged in." @default.
• W2952006246 created "2019-06-27" @default.
• W2952006246 creator A5035901640 @default.
• W2952006246 creator A5037414134 @default.
• W2952006246 creator A5049161422 @default.
• W2952006246 creator A5063581021 @default.
• W2952006246 creator A5074552284 @default.
• W2952006246 date "2016-11-16" @default.
• W2952006246 modified "2023-09-27" @default.
• W2952006246 title "Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering" @default.
• W2952006246 cites W1503398984 @default.
• W2952006246 cites W1594453127 @default.
• W2952006246 cites W1663973292 @default.
• W2952006246 cites W1691728462 @default.
• W2952006246 cites W1850742715 @default.
• W2952006246 cites W1950831375 @default.
• W2952006246 cites W1959608418 @default.
• W2952006246 cites W1975998725 @default.
• W2952006246 cites W2025147484 @default.
• W2952006246 cites W2057907879 @default.
• W2952006246 cites W2098318489 @default.
• W2952006246 cites W2099471712 @default.
• W2952006246 cites W2100495367 @default.
• W2952006246 cites W2101234009 @default.
• W2952006246 cites W2102625004 @default.
• W2952006246 cites W2112796928 @default.
• W2952006246 cites W2118858186 @default.
• W2952006246 cites W2121947440 @default.
• W2952006246 cites W2125389028 @default.
• W2952006246 cites W2129793592 @default.
• W2952006246 cites W2130293653 @default.
• W2952006246 cites W2132771435 @default.
• W2952006246 cites W2133564696 @default.
• W2952006246 cites W2135674549 @default.
• W2952006246 cites W2141461755 @default.
• W2952006246 cites W2145094598 @default.
• W2952006246 cites W2147768505 @default.
• W2952006246 cites W2150102617 @default.
• W2952006246 cites W2165874743 @default.
• W2952006246 cites W2187089797 @default.
• W2952006246 cites W2194775991 @default.
• W2952006246 cites W2395149821 @default.
• W2952006246 cites W2432004435 @default.
• W2952006246 cites W2949416428 @default.
• W2952006246 cites W2950447478 @default.
• W2952006246 cites W2951140085 @default.
• W2952006246 cites W2951523806 @default.
• W2952006246 cites W2953318193 @default.
• W2952006246 cites W2963174698 @default.
• W2952006246 cites W2963684088 @default.
• W2952006246 cites W2964074409 @default.
• W2952006246 cites W2964121744 @default.
• W2952006246 cites W3038022805 @default.
• W2952006246 doi "https://doi.org/10.48550/arxiv.1611.05148" @default.
• W2952006246 hasPublicationYear "2016" @default.
• W2952006246 type Work @default.
• W2952006246 sameAs 2952006246 @default.
• W2952006246 citedByCount "49" @default.
• W2952006246 countsByYear W29520062462017 @default.
• W2952006246 countsByYear W29520062462018 @default.
• W2952006246 countsByYear W29520062462019 @default.
• W2952006246 countsByYear W29520062462020 @default.
• W2952006246 countsByYear W29520062462021 @default.
• W2952006246 countsByYear W29520062462022 @default.
• W2952006246 countsByYear W29520062462023 @default.
• W2952006246 crossrefType "posted-content" @default.
• W2952006246 hasAuthorship W2952006246A5035901640 @default.
• W2952006246 hasAuthorship W2952006246A5037414134 @default.
• W2952006246 hasAuthorship W2952006246A5049161422 @default.
• W2952006246 hasAuthorship W2952006246A5063581021 @default.
• W2952006246 hasAuthorship W2952006246A5074552284 @default.
• W2952006246 hasBestOaLocation W29520062461 @default.
• W2952006246 hasConcept C101738243 @default.
• W2952006246 hasConcept C119857082 @default.
• W2952006246 hasConcept C153180895 @default.
• W2952006246 hasConcept C154945302 @default.
• W2952006246 hasConcept C167966045 @default.
• W2952006246 hasConcept C39890363 @default.
• W2952006246 hasConcept C41008148 @default.
• W2952006246 hasConcept C41608201 @default.
• W2952006246 hasConcept C50644808 @default.
• W2952006246 hasConcept C61224824 @default.
• W2952006246 hasConcept C73555534 @default.
• W2952006246 hasConceptScore W2952006246C101738243 @default.
• W2952006246 hasConceptScore W2952006246C119857082 @default.
• W2952006246 hasConceptScore W2952006246C153180895 @default.
• W2952006246 hasConceptScore W2952006246C154945302 @default.
• W2952006246 hasConceptScore W2952006246C167966045 @default.
• W2952006246 hasConceptScore W2952006246C39890363 @default.
• W2952006246 hasConceptScore W2952006246C41008148 @default.
• W2952006246 hasConceptScore W2952006246C41608201 @default.
• W2952006246 hasConceptScore W2952006246C50644808 @default.
• W2952006246 hasConceptScore W2952006246C61224824 @default.
• W2952006246 hasConceptScore W2952006246C73555534 @default.
• W2952006246 hasLocation W29520062461 @default.
• W2952006246 hasLocation W29520062462 @default.
• W2952006246 hasOpenAccess W2952006246 @default.
• W2952006246 hasPrimaryLocation W29520062461 @default.
• W2952006246 hasRelatedWork W2335364074 @default.
• W2952006246 hasRelatedWork W2556467266 @default.

• next