Matches in SemOpenAlex for { <https://semopenalex.org/work/W3005028579> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3005028579 abstract "Deep clustering achieves unprecedented levels of accuracy with unsupervised feature extraction on rich datasets where the joint statistics of the latent space is learned via highly nonlinear compression. This paper has two separate contributions to this field. First, we conduct an extensive and first-of-its-kind empirical study on the statistical relationship between the clustering accuracy and image reconstruction quality of a state-of-the-art deep clustering topology in the form of a convolutional variational autoencoder (VAE) with a K-means back end. We change the latent variable $z$ at the bottleneck of the network to create different latent dimensions and explore how clustering performance metrics and reconstruction metrics are statistically related. Secondly, based on our data-driven statistical findings, we also propose a novel cost function for the VAE which includes the structural similarity index measure to jointly optimize image quality and latent statistics for improved clustering. The preliminary results show significant increases in clustering accuracy of as much as 10.76% on two popular benchmark datasets. The TensorFlow implementation for the experimental framework can be found here: https://github.com/alla15747/IEEE-Comparitive-Study-VAE-Paper- (Python code will be available at the time of publication)." @default.
- W3005028579 created "2020-02-14" @default.
- W3005028579 creator A5050813414 @default.
- W3005028579 creator A5073587241 @default.
- W3005028579 date "2020-01-01" @default.
- W3005028579 modified "2023-09-23" @default.
- W3005028579 title "A Statistical Comparative Study on Image Reconstruction and Clustering With Novel VAE Cost Function" @default.
- W3005028579 cites W1585655587 @default.
- W3005028579 cites W163225181 @default.
- W3005028579 cites W1691728462 @default.
- W3005028579 cites W1850742715 @default.
- W3005028579 cites W1959608418 @default.
- W3005028579 cites W1990643970 @default.
- W3005028579 cites W2017257315 @default.
- W3005028579 cites W2025768430 @default.
- W3005028579 cites W2095705004 @default.
- W3005028579 cites W2100495367 @default.
- W3005028579 cites W2120303002 @default.
- W3005028579 cites W2133257461 @default.
- W3005028579 cites W2133665775 @default.
- W3005028579 cites W2136922672 @default.
- W3005028579 cites W2149230623 @default.
- W3005028579 cites W2150593711 @default.
- W3005028579 cites W2156483112 @default.
- W3005028579 cites W2159269332 @default.
- W3005028579 cites W2165874743 @default.
- W3005028579 cites W2188365844 @default.
- W3005028579 cites W2218318129 @default.
- W3005028579 cites W2221409856 @default.
- W3005028579 cites W2405933695 @default.
- W3005028579 cites W2527569769 @default.
- W3005028579 cites W2533545350 @default.
- W3005028579 cites W2603986758 @default.
- W3005028579 cites W2620025707 @default.
- W3005028579 cites W2753738274 @default.
- W3005028579 cites W2884851420 @default.
- W3005028579 cites W2900404321 @default.
- W3005028579 cites W2949416428 @default.
- W3005028579 cites W2952673310 @default.
- W3005028579 cites W2963365397 @default.
- W3005028579 cites W2964074409 @default.
- W3005028579 cites W2964121744 @default.
- W3005028579 cites W2964167449 @default.
- W3005028579 cites W3098957257 @default.
- W3005028579 cites W3101749733 @default.
- W3005028579 doi "https://doi.org/10.1109/access.2020.2971270" @default.
- W3005028579 hasPublicationYear "2020" @default.
- W3005028579 type Work @default.
- W3005028579 sameAs 3005028579 @default.
- W3005028579 citedByCount "1" @default.
- W3005028579 countsByYear W30050285792022 @default.
- W3005028579 crossrefType "journal-article" @default.
- W3005028579 hasAuthorship W3005028579A5050813414 @default.
- W3005028579 hasAuthorship W3005028579A5073587241 @default.
- W3005028579 hasBestOaLocation W30050285791 @default.
- W3005028579 hasConcept C101738243 @default.
- W3005028579 hasConcept C108583219 @default.
- W3005028579 hasConcept C124101348 @default.
- W3005028579 hasConcept C153180895 @default.
- W3005028579 hasConcept C154945302 @default.
- W3005028579 hasConcept C33704608 @default.
- W3005028579 hasConcept C41008148 @default.
- W3005028579 hasConcept C73555534 @default.
- W3005028579 hasConcept C94641424 @default.
- W3005028579 hasConceptScore W3005028579C101738243 @default.
- W3005028579 hasConceptScore W3005028579C108583219 @default.
- W3005028579 hasConceptScore W3005028579C124101348 @default.
- W3005028579 hasConceptScore W3005028579C153180895 @default.
- W3005028579 hasConceptScore W3005028579C154945302 @default.
- W3005028579 hasConceptScore W3005028579C33704608 @default.
- W3005028579 hasConceptScore W3005028579C41008148 @default.
- W3005028579 hasConceptScore W3005028579C73555534 @default.
- W3005028579 hasConceptScore W3005028579C94641424 @default.
- W3005028579 hasLocation W30050285791 @default.
- W3005028579 hasOpenAccess W3005028579 @default.
- W3005028579 hasPrimaryLocation W30050285791 @default.
- W3005028579 hasRelatedWork W10542589 @default.
- W3005028579 hasRelatedWork W10568412 @default.
- W3005028579 hasRelatedWork W10636026 @default.
- W3005028579 hasRelatedWork W10939515 @default.
- W3005028579 hasRelatedWork W11684367 @default.
- W3005028579 hasRelatedWork W13324992 @default.
- W3005028579 hasRelatedWork W2390764 @default.
- W3005028579 hasRelatedWork W4711283 @default.
- W3005028579 hasRelatedWork W6981299 @default.
- W3005028579 hasRelatedWork W746201 @default.
- W3005028579 isParatext "false" @default.
- W3005028579 isRetracted "false" @default.
- W3005028579 magId "3005028579" @default.
- W3005028579 workType "article" @default.