Matches in SemOpenAlex for { <https://semopenalex.org/work/W2921416943> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2921416943 endingPage "42031" @default.
- W2921416943 startingPage "42024" @default.
- W2921416943 abstract "With the development of deep convolutional neural networks in recent years, the network structure has become more and more complicated and varied, and there are very good results in pattern recognition, image classification, scene classification, and target tracking. This end-to-end learning model relies on the initial large dataset. However, many data are gradually obtained in practical situations, which contradict the deep learning of one-time batch learning. There is an urgent need for an incremental learning approach that can continuously learn new knowledge from new data while retaining what has already been learned. This paper proposes an incremental learning algorithm based on convolutional neural network and support vector data description. CNN and AM-Softmax loss function are used to represent and continuously learn image features. Support vector data description is used to construct multiple hyperspheres for new and old classes of images. Class-incremental learning is achieved by the increment of hyperspheres. The experimental results show that the incremental learning method proposed in this paper can effectively extract the latent features of the image and adapt it to the learning situation of the class-increment. The recognition accuracy is close to batch learning." @default.
- W2921416943 created "2019-03-22" @default.
- W2921416943 creator A5028518753 @default.
- W2921416943 creator A5062394357 @default.
- W2921416943 date "2019-01-01" @default.
- W2921416943 modified "2023-10-14" @default.
- W2921416943 title "Class-Incremental Learning Based on Feature Extraction of CNN With Optimized Softmax and One-Class Classifiers" @default.
- W2921416943 cites W1499991161 @default.
- W2921416943 cites W1509092951 @default.
- W2921416943 cites W1554485105 @default.
- W2921416943 cites W1560215624 @default.
- W2921416943 cites W1682403713 @default.
- W2921416943 cites W1970088130 @default.
- W2921416943 cites W2103753221 @default.
- W2921416943 cites W2112841646 @default.
- W2921416943 cites W2132641846 @default.
- W2921416943 cites W2144276202 @default.
- W2921416943 cites W2160684493 @default.
- W2921416943 cites W2194775991 @default.
- W2921416943 cites W2257979135 @default.
- W2921416943 cites W2546945975 @default.
- W2921416943 cites W2964137095 @default.
- W2921416943 cites W2964189064 @default.
- W2921416943 cites W3103152812 @default.
- W2921416943 doi "https://doi.org/10.1109/access.2019.2904614" @default.
- W2921416943 hasPublicationYear "2019" @default.
- W2921416943 type Work @default.
- W2921416943 sameAs 2921416943 @default.
- W2921416943 citedByCount "13" @default.
- W2921416943 countsByYear W29214169432019 @default.
- W2921416943 countsByYear W29214169432020 @default.
- W2921416943 countsByYear W29214169432021 @default.
- W2921416943 countsByYear W29214169432022 @default.
- W2921416943 countsByYear W29214169432023 @default.
- W2921416943 crossrefType "journal-article" @default.
- W2921416943 hasAuthorship W2921416943A5028518753 @default.
- W2921416943 hasAuthorship W2921416943A5062394357 @default.
- W2921416943 hasBestOaLocation W29214169431 @default.
- W2921416943 hasConcept C108583219 @default.
- W2921416943 hasConcept C119857082 @default.
- W2921416943 hasConcept C138885662 @default.
- W2921416943 hasConcept C153180895 @default.
- W2921416943 hasConcept C154945302 @default.
- W2921416943 hasConcept C188441871 @default.
- W2921416943 hasConcept C2776401178 @default.
- W2921416943 hasConcept C2777212361 @default.
- W2921416943 hasConcept C2780735816 @default.
- W2921416943 hasConcept C41008148 @default.
- W2921416943 hasConcept C41895202 @default.
- W2921416943 hasConcept C52622490 @default.
- W2921416943 hasConcept C59404180 @default.
- W2921416943 hasConcept C81363708 @default.
- W2921416943 hasConceptScore W2921416943C108583219 @default.
- W2921416943 hasConceptScore W2921416943C119857082 @default.
- W2921416943 hasConceptScore W2921416943C138885662 @default.
- W2921416943 hasConceptScore W2921416943C153180895 @default.
- W2921416943 hasConceptScore W2921416943C154945302 @default.
- W2921416943 hasConceptScore W2921416943C188441871 @default.
- W2921416943 hasConceptScore W2921416943C2776401178 @default.
- W2921416943 hasConceptScore W2921416943C2777212361 @default.
- W2921416943 hasConceptScore W2921416943C2780735816 @default.
- W2921416943 hasConceptScore W2921416943C41008148 @default.
- W2921416943 hasConceptScore W2921416943C41895202 @default.
- W2921416943 hasConceptScore W2921416943C52622490 @default.
- W2921416943 hasConceptScore W2921416943C59404180 @default.
- W2921416943 hasConceptScore W2921416943C81363708 @default.
- W2921416943 hasLocation W29214169431 @default.
- W2921416943 hasOpenAccess W2921416943 @default.
- W2921416943 hasPrimaryLocation W29214169431 @default.
- W2921416943 hasRelatedWork W2279398222 @default.
- W2921416943 hasRelatedWork W2546942002 @default.
- W2921416943 hasRelatedWork W2592385986 @default.
- W2921416943 hasRelatedWork W2771515600 @default.
- W2921416943 hasRelatedWork W2782592381 @default.
- W2921416943 hasRelatedWork W2946016983 @default.
- W2921416943 hasRelatedWork W2977314777 @default.
- W2921416943 hasRelatedWork W3156786002 @default.
- W2921416943 hasRelatedWork W4299822940 @default.
- W2921416943 hasRelatedWork W4366492315 @default.
- W2921416943 hasVolume "7" @default.
- W2921416943 isParatext "false" @default.
- W2921416943 isRetracted "false" @default.
- W2921416943 magId "2921416943" @default.
- W2921416943 workType "article" @default.