Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049765744> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3049765744 endingPage "3260" @default.
- W3049765744 startingPage "3244" @default.
- W3049765744 abstract "Image classification is an important part of pattern recognition. With the development of convolutional neural networks (CNNs), many CNN methods are proposed, which have a large number of samples for training, which can have high performance. However, there may exist limited samples in some real-world applications. In order to improve the performance of CNN learning with insufficient samples, this article proposes a new method called the classifier method based on a variational autoencoder (CFVAE), which is comprised of two parts: 1) a standard CNN as a prior classifier and 2) a CNN based on variational autoencoder (VAE) as a posterior classifier. First, the prior classifier is utilized to generate the prior label and information about distributions of latent variables; and the posterior classifier is trained to augment some latent variables from regularized distributions to improve the performance. Second, we also present the uniform objective function of CFVAE and put forward an optimization method based on the stochastic gradient variational Bayes method to solve the objective model. Third, we analyze the feasibility of CFVAE based on Hoeffding's inequality and Chernoff's bounding method. This analysis indicates that the latent variables augmentation method based on regularized latent variables distributions can generate samples fitting well with the distribution of data such that the proposed method can improve the performance of CNN with insufficient samples. Finally, the experiments manifest that our proposed CFVAE can provide more accurate performance than state-of-the-art methods." @default.
- W3049765744 created "2020-08-21" @default.
- W3049765744 creator A5009705946 @default.
- W3049765744 creator A5049727437 @default.
- W3049765744 creator A5090815103 @default.
- W3049765744 creator A5090873606 @default.
- W3049765744 date "2022-05-01" @default.
- W3049765744 modified "2023-10-17" @default.
- W3049765744 title "An Efficient Image Categorization Method With Insufficient Training Samples" @default.
- W3049765744 cites W1677182931 @default.
- W3049765744 cites W1903029394 @default.
- W3049765744 cites W1920235975 @default.
- W3049765744 cites W2050398567 @default.
- W3049765744 cites W2053229256 @default.
- W3049765744 cites W2071039340 @default.
- W3049765744 cites W2097117768 @default.
- W3049765744 cites W2109191808 @default.
- W3049765744 cites W2112796928 @default.
- W3049765744 cites W2134557905 @default.
- W3049765744 cites W2136634080 @default.
- W3049765744 cites W2147944429 @default.
- W3049765744 cites W2183341477 @default.
- W3049765744 cites W2194775991 @default.
- W3049765744 cites W2211629196 @default.
- W3049765744 cites W2214352687 @default.
- W3049765744 cites W2583938035 @default.
- W3049765744 cites W2593172378 @default.
- W3049765744 cites W2603142085 @default.
- W3049765744 cites W2904444765 @default.
- W3049765744 cites W2906666325 @default.
- W3049765744 cites W2911882878 @default.
- W3049765744 cites W2962932094 @default.
- W3049765744 cites W2962951611 @default.
- W3049765744 cites W2963101867 @default.
- W3049765744 cites W2963246109 @default.
- W3049765744 cites W2963564750 @default.
- W3049765744 cites W2964105864 @default.
- W3049765744 cites W2969836179 @default.
- W3049765744 cites W2987221721 @default.
- W3049765744 cites W2988720209 @default.
- W3049765744 cites W2994633389 @default.
- W3049765744 cites W3102431071 @default.
- W3049765744 doi "https://doi.org/10.1109/tcyb.2020.3011165" @default.
- W3049765744 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32780710" @default.
- W3049765744 hasPublicationYear "2022" @default.
- W3049765744 type Work @default.
- W3049765744 sameAs 3049765744 @default.
- W3049765744 citedByCount "5" @default.
- W3049765744 countsByYear W30497657442020 @default.
- W3049765744 countsByYear W30497657442022 @default.
- W3049765744 countsByYear W30497657442023 @default.
- W3049765744 crossrefType "journal-article" @default.
- W3049765744 hasAuthorship W3049765744A5009705946 @default.
- W3049765744 hasAuthorship W3049765744A5049727437 @default.
- W3049765744 hasAuthorship W3049765744A5090815103 @default.
- W3049765744 hasAuthorship W3049765744A5090873606 @default.
- W3049765744 hasConcept C101738243 @default.
- W3049765744 hasConcept C119857082 @default.
- W3049765744 hasConcept C153180895 @default.
- W3049765744 hasConcept C154945302 @default.
- W3049765744 hasConcept C41008148 @default.
- W3049765744 hasConcept C50644808 @default.
- W3049765744 hasConcept C51167844 @default.
- W3049765744 hasConcept C63584917 @default.
- W3049765744 hasConcept C81363708 @default.
- W3049765744 hasConcept C95623464 @default.
- W3049765744 hasConceptScore W3049765744C101738243 @default.
- W3049765744 hasConceptScore W3049765744C119857082 @default.
- W3049765744 hasConceptScore W3049765744C153180895 @default.
- W3049765744 hasConceptScore W3049765744C154945302 @default.
- W3049765744 hasConceptScore W3049765744C41008148 @default.
- W3049765744 hasConceptScore W3049765744C50644808 @default.
- W3049765744 hasConceptScore W3049765744C51167844 @default.
- W3049765744 hasConceptScore W3049765744C63584917 @default.
- W3049765744 hasConceptScore W3049765744C81363708 @default.
- W3049765744 hasConceptScore W3049765744C95623464 @default.
- W3049765744 hasFunder F4320321001 @default.
- W3049765744 hasFunder F4320321921 @default.
- W3049765744 hasIssue "5" @default.
- W3049765744 hasLocation W30497657441 @default.
- W3049765744 hasLocation W30497657442 @default.
- W3049765744 hasOpenAccess W3049765744 @default.
- W3049765744 hasPrimaryLocation W30497657441 @default.
- W3049765744 hasRelatedWork W2112343299 @default.
- W3049765744 hasRelatedWork W2776466379 @default.
- W3049765744 hasRelatedWork W2995914718 @default.
- W3049765744 hasRelatedWork W2998168123 @default.
- W3049765744 hasRelatedWork W3049765744 @default.
- W3049765744 hasRelatedWork W3134637941 @default.
- W3049765744 hasRelatedWork W4220775285 @default.
- W3049765744 hasRelatedWork W4221015625 @default.
- W3049765744 hasRelatedWork W4287995534 @default.
- W3049765744 hasRelatedWork W564581980 @default.
- W3049765744 hasVolume "52" @default.
- W3049765744 isParatext "false" @default.
- W3049765744 isRetracted "false" @default.
- W3049765744 magId "3049765744" @default.
- W3049765744 workType "article" @default.