Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997163612> ?p ?o ?g. }
- W2997163612 abstract "In recent years, many cutting-edge research results have emerged in the field of computer vision, especially in the field of image classification. But, researchers are still trying to explore more sophisticated models to further improve the accuracy of image classification. However, many models have failed to achieve satisfactory results due to the complexity of the image and the problems of image noise. Therefore, in order to solve these problems, this paper proposes an unsupervised feature extraction method called multi-granularity convolution denoising autoencoder (MGCDAE). Based on convolutional neural network, the method proposed the concept of multi-granularity convolution kernel to solve the problem of complex image feature extraction. In addition, we introduce denoising autoencoder (DAE) for image noise, which enables our approach to extract more robust features from noise images. The high-level features extracted by the above method are sent to the softmax classifier for classification to evaluate the validity of the feature extraction. Our method has been evaluated on three benchmark data sets, which results show that our approach can extract more discriminative high-level features compared with other existing algorithms." @default.
- W2997163612 created "2020-01-10" @default.
- W2997163612 creator A5010969856 @default.
- W2997163612 creator A5017670508 @default.
- W2997163612 creator A5017941291 @default.
- W2997163612 date "2019-06-01" @default.
- W2997163612 modified "2023-09-26" @default.
- W2997163612 title "An Unsupervised Feature Extraction Method based on Multi-granularity Convolution Denoising Autoencoder" @default.
- W2997163612 cites W1498436455 @default.
- W2997163612 cites W1534477342 @default.
- W2997163612 cites W1545641654 @default.
- W2997163612 cites W1799366690 @default.
- W2997163612 cites W1832069583 @default.
- W2997163612 cites W1973445088 @default.
- W2997163612 cites W1993660315 @default.
- W2997163612 cites W2004083143 @default.
- W2997163612 cites W2017257315 @default.
- W2997163612 cites W2025768430 @default.
- W2997163612 cites W2061979569 @default.
- W2997163612 cites W2072128103 @default.
- W2997163612 cites W2097117768 @default.
- W2997163612 cites W2100002341 @default.
- W2997163612 cites W2100846049 @default.
- W2997163612 cites W2112796928 @default.
- W2997163612 cites W2121238376 @default.
- W2997163612 cites W2136655611 @default.
- W2997163612 cites W2143915663 @default.
- W2997163612 cites W2155916898 @default.
- W2997163612 cites W2189540548 @default.
- W2997163612 cites W2294189222 @default.
- W2997163612 cites W2338231020 @default.
- W2997163612 cites W2608706647 @default.
- W2997163612 cites W2768045609 @default.
- W2997163612 cites W2769674252 @default.
- W2997163612 cites W2776990447 @default.
- W2997163612 cites W2794937634 @default.
- W2997163612 cites W2798854001 @default.
- W2997163612 cites W2891881637 @default.
- W2997163612 cites W2912889105 @default.
- W2997163612 cites W2919115771 @default.
- W2997163612 cites W2949705273 @default.
- W2997163612 cites W3118608800 @default.
- W2997163612 doi "https://doi.org/10.1109/icis46139.2019.8940316" @default.
- W2997163612 hasPublicationYear "2019" @default.
- W2997163612 type Work @default.
- W2997163612 sameAs 2997163612 @default.
- W2997163612 citedByCount "0" @default.
- W2997163612 crossrefType "proceedings-article" @default.
- W2997163612 hasAuthorship W2997163612A5010969856 @default.
- W2997163612 hasAuthorship W2997163612A5017670508 @default.
- W2997163612 hasAuthorship W2997163612A5017941291 @default.
- W2997163612 hasConcept C101738243 @default.
- W2997163612 hasConcept C111919701 @default.
- W2997163612 hasConcept C114614502 @default.
- W2997163612 hasConcept C138885662 @default.
- W2997163612 hasConcept C153180895 @default.
- W2997163612 hasConcept C154945302 @default.
- W2997163612 hasConcept C177774035 @default.
- W2997163612 hasConcept C188441871 @default.
- W2997163612 hasConcept C2776401178 @default.
- W2997163612 hasConcept C33923547 @default.
- W2997163612 hasConcept C41008148 @default.
- W2997163612 hasConcept C41895202 @default.
- W2997163612 hasConcept C45347329 @default.
- W2997163612 hasConcept C50644808 @default.
- W2997163612 hasConcept C52622490 @default.
- W2997163612 hasConcept C74193536 @default.
- W2997163612 hasConcept C81363708 @default.
- W2997163612 hasConcept C97931131 @default.
- W2997163612 hasConceptScore W2997163612C101738243 @default.
- W2997163612 hasConceptScore W2997163612C111919701 @default.
- W2997163612 hasConceptScore W2997163612C114614502 @default.
- W2997163612 hasConceptScore W2997163612C138885662 @default.
- W2997163612 hasConceptScore W2997163612C153180895 @default.
- W2997163612 hasConceptScore W2997163612C154945302 @default.
- W2997163612 hasConceptScore W2997163612C177774035 @default.
- W2997163612 hasConceptScore W2997163612C188441871 @default.
- W2997163612 hasConceptScore W2997163612C2776401178 @default.
- W2997163612 hasConceptScore W2997163612C33923547 @default.
- W2997163612 hasConceptScore W2997163612C41008148 @default.
- W2997163612 hasConceptScore W2997163612C41895202 @default.
- W2997163612 hasConceptScore W2997163612C45347329 @default.
- W2997163612 hasConceptScore W2997163612C50644808 @default.
- W2997163612 hasConceptScore W2997163612C52622490 @default.
- W2997163612 hasConceptScore W2997163612C74193536 @default.
- W2997163612 hasConceptScore W2997163612C81363708 @default.
- W2997163612 hasConceptScore W2997163612C97931131 @default.
- W2997163612 hasLocation W29971636121 @default.
- W2997163612 hasOpenAccess W2997163612 @default.
- W2997163612 hasPrimaryLocation W29971636121 @default.
- W2997163612 hasRelatedWork W1920962657 @default.
- W2997163612 hasRelatedWork W1982867989 @default.
- W2997163612 hasRelatedWork W2033713712 @default.
- W2997163612 hasRelatedWork W2088610186 @default.
- W2997163612 hasRelatedWork W2153795334 @default.
- W2997163612 hasRelatedWork W2292254049 @default.
- W2997163612 hasRelatedWork W2518029102 @default.
- W2997163612 hasRelatedWork W2549665044 @default.
- W2997163612 hasRelatedWork W2556437746 @default.
- W2997163612 hasRelatedWork W2739587484 @default.