Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129469957> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W3129469957 abstract "Unsupervised representation learning is essential in the field of machine learning, and accurate neighbor clusters of representation show great potential to support unsupervised image classification. This paper proposes a VAE (Variational Autoencoder) based network and a clustering method to achieve adaptive neighbor clustering to support the self-supervised classification. The proposed network encodes the image into the representation with boundary information, and the proposed cluster method takes advantage of the boundary information to deliver adaptive neighbor cluster results. Experimental evaluations show that the proposed method outperforms state-of-the-art representation learning methods in terms of neighbor clustering accuracy. Particularly, AC-VAE achieves 95% and 82% accuracy on CIFAR10 dataset when the average neighbor cluster sizes are 10 and 100. Furthermore, the neighbor cluster results are found converge within the clustering range (α≤2), and the converged neighbor clusters are used to support the self-supervised classification. The proposed method delivers classification results that are competitive with the state-of-the-art and reduces the super parameter k in KNN (K-nearest neighbor), which is often used in self-supervised classification." @default.
- W3129469957 created "2021-03-01" @default.
- W3129469957 creator A5003642180 @default.
- W3129469957 creator A5014190578 @default.
- W3129469957 creator A5020029411 @default.
- W3129469957 creator A5048069849 @default.
- W3129469957 date "2021-05-04" @default.
- W3129469957 modified "2023-09-23" @default.
- W3129469957 title "AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering" @default.
- W3129469957 hasPublicationYear "2021" @default.
- W3129469957 type Work @default.
- W3129469957 sameAs 3129469957 @default.
- W3129469957 citedByCount "0" @default.
- W3129469957 crossrefType "journal-article" @default.
- W3129469957 hasAuthorship W3129469957A5003642180 @default.
- W3129469957 hasAuthorship W3129469957A5014190578 @default.
- W3129469957 hasAuthorship W3129469957A5020029411 @default.
- W3129469957 hasAuthorship W3129469957A5048069849 @default.
- W3129469957 hasConcept C101738243 @default.
- W3129469957 hasConcept C113238511 @default.
- W3129469957 hasConcept C119857082 @default.
- W3129469957 hasConcept C153180895 @default.
- W3129469957 hasConcept C154945302 @default.
- W3129469957 hasConcept C17744445 @default.
- W3129469957 hasConcept C199539241 @default.
- W3129469957 hasConcept C2776359362 @default.
- W3129469957 hasConcept C41008148 @default.
- W3129469957 hasConcept C50644808 @default.
- W3129469957 hasConcept C59404180 @default.
- W3129469957 hasConcept C73555534 @default.
- W3129469957 hasConcept C8038995 @default.
- W3129469957 hasConcept C94625758 @default.
- W3129469957 hasConceptScore W3129469957C101738243 @default.
- W3129469957 hasConceptScore W3129469957C113238511 @default.
- W3129469957 hasConceptScore W3129469957C119857082 @default.
- W3129469957 hasConceptScore W3129469957C153180895 @default.
- W3129469957 hasConceptScore W3129469957C154945302 @default.
- W3129469957 hasConceptScore W3129469957C17744445 @default.
- W3129469957 hasConceptScore W3129469957C199539241 @default.
- W3129469957 hasConceptScore W3129469957C2776359362 @default.
- W3129469957 hasConceptScore W3129469957C41008148 @default.
- W3129469957 hasConceptScore W3129469957C50644808 @default.
- W3129469957 hasConceptScore W3129469957C59404180 @default.
- W3129469957 hasConceptScore W3129469957C73555534 @default.
- W3129469957 hasConceptScore W3129469957C8038995 @default.
- W3129469957 hasConceptScore W3129469957C94625758 @default.
- W3129469957 hasLocation W31294699571 @default.
- W3129469957 hasOpenAccess W3129469957 @default.
- W3129469957 hasPrimaryLocation W31294699571 @default.
- W3129469957 hasRelatedWork W1583988398 @default.
- W3129469957 hasRelatedWork W2012955012 @default.
- W3129469957 hasRelatedWork W2050500507 @default.
- W3129469957 hasRelatedWork W2053468381 @default.
- W3129469957 hasRelatedWork W2098175874 @default.
- W3129469957 hasRelatedWork W2103952102 @default.
- W3129469957 hasRelatedWork W2106673546 @default.
- W3129469957 hasRelatedWork W2112034323 @default.
- W3129469957 hasRelatedWork W2120835067 @default.
- W3129469957 hasRelatedWork W2133830320 @default.
- W3129469957 hasRelatedWork W2139701438 @default.
- W3129469957 hasRelatedWork W2168592605 @default.
- W3129469957 hasRelatedWork W2170137966 @default.
- W3129469957 hasRelatedWork W2172189177 @default.
- W3129469957 hasRelatedWork W2219637520 @default.
- W3129469957 hasRelatedWork W2358843920 @default.
- W3129469957 hasRelatedWork W2377982443 @default.
- W3129469957 hasRelatedWork W2759144750 @default.
- W3129469957 hasRelatedWork W2810357052 @default.
- W3129469957 hasRelatedWork W2969383965 @default.
- W3129469957 isParatext "false" @default.
- W3129469957 isRetracted "false" @default.
- W3129469957 magId "3129469957" @default.
- W3129469957 workType "article" @default.