FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2973001052> ?p ?o ?g. }

• W2973001052 endingPage "2902" @default.
• W2973001052 startingPage "2889" @default.
• W2973001052 abstract "Group convolution is widely used in many mobile networks to remove the filter's redundancy from the channel extent. In order to further reduce the redundancy of group convolution, this article proposes a novel repeated group convolutional (RGC) kernel, which has M primary groups, and each primary group includes N tiny groups. In every primary group, the same convolutional kernel is repeated in all the tiny groups. The RGC filter is the first kernel to remove the redundancy from group extent. Based on RGC, a sparse RGC (SRGC) kernel is also introduced in this article, and its corresponding network is called SRGC neural networks (SRGC-Net). The SRGC kernel is the summation of RGC kernel and pointwise group convolutional (PGC) kernel. The number of PGC's groups is M. Accordingly, in each primary group, besides the center locations in all channels, the values of parameters located in other N -1 tiny groups are all zero. Therefore, SRGC can significantly reduce the parameters. Moreover, it can also effectively retrieve spatial and channel-difference features by utilizing RGC and PGC to preserve the richness of produced features. Comparative experiments were performed on the benchmark classification data sets. Compared with the traditional popular networks, SRGC-Nets can perform better with timely reducing the model size and computational complexity. Furthermore, it can also achieve better performances than other latest state-of-the-art mobile networks on most of the databases and effectively decrease the test and training runtime." @default.
• W2973001052 created "2019-09-19" @default.
• W2973001052 creator A5004565086 @default.
• W2973001052 creator A5019972814 @default.
• W2973001052 creator A5030843117 @default.
• W2973001052 creator A5063057774 @default.
• W2973001052 creator A5075496043 @default.
• W2973001052 date "2020-08-01" @default.
• W2973001052 modified "2023-10-15" @default.
• W2973001052 title "SRGC-Nets: Sparse Repeated Group Convolutional Neural Networks" @default.
• W2973001052 cites W2106721790 @default.
• W2973001052 cites W2108598243 @default.
• W2973001052 cites W2142105298 @default.
• W2973001052 cites W2145607950 @default.
• W2973001052 cites W2149494476 @default.
• W2973001052 cites W2183341477 @default.
• W2973001052 cites W2194775991 @default.
• W2973001052 cites W2233116163 @default.
• W2973001052 cites W2300242332 @default.
• W2973001052 cites W2302255633 @default.
• W2973001052 cites W2331143823 @default.
• W2973001052 cites W2400429454 @default.
• W2973001052 cites W2531409750 @default.
• W2973001052 cites W2549139847 @default.
• W2973001052 cites W2554302513 @default.
• W2973001052 cites W2606967921 @default.
• W2973001052 cites W2758000438 @default.
• W2973001052 cites W2778955544 @default.
• W2973001052 cites W2793950911 @default.
• W2973001052 cites W2883780447 @default.
• W2973001052 cites W2963125010 @default.
• W2973001052 cites W2963163009 @default.
• W2973001052 cites W2963216524 @default.
• W2973001052 cites W2963363373 @default.
• W2973001052 cites W2963446712 @default.
• W2973001052 cites W2964137095 @default.
• W2973001052 cites W2964233199 @default.
• W2973001052 doi "https://doi.org/10.1109/tnnls.2019.2933665" @default.
• W2973001052 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31502989" @default.
• W2973001052 hasPublicationYear "2020" @default.
• W2973001052 type Work @default.
• W2973001052 sameAs 2973001052 @default.
• W2973001052 citedByCount "19" @default.
• W2973001052 countsByYear W29730010522020 @default.
• W2973001052 countsByYear W29730010522021 @default.
• W2973001052 countsByYear W29730010522022 @default.
• W2973001052 countsByYear W29730010522023 @default.
• W2973001052 crossrefType "journal-article" @default.
• W2973001052 hasAuthorship W2973001052A5004565086 @default.
• W2973001052 hasAuthorship W2973001052A5019972814 @default.
• W2973001052 hasAuthorship W2973001052A5030843117 @default.
• W2973001052 hasAuthorship W2973001052A5063057774 @default.
• W2973001052 hasAuthorship W2973001052A5075496043 @default.
• W2973001052 hasConcept C111919701 @default.
• W2973001052 hasConcept C11413529 @default.
• W2973001052 hasConcept C118615104 @default.
• W2973001052 hasConcept C13280743 @default.
• W2973001052 hasConcept C134306372 @default.
• W2973001052 hasConcept C152124472 @default.
• W2973001052 hasConcept C153180895 @default.
• W2973001052 hasConcept C154945302 @default.
• W2973001052 hasConcept C185798385 @default.
• W2973001052 hasConcept C205649164 @default.
• W2973001052 hasConcept C2777984123 @default.
• W2973001052 hasConcept C33923547 @default.
• W2973001052 hasConcept C41008148 @default.
• W2973001052 hasConcept C45347329 @default.
• W2973001052 hasConcept C50644808 @default.
• W2973001052 hasConcept C74193536 @default.
• W2973001052 hasConcept C81363708 @default.
• W2973001052 hasConceptScore W2973001052C111919701 @default.
• W2973001052 hasConceptScore W2973001052C11413529 @default.
• W2973001052 hasConceptScore W2973001052C118615104 @default.
• W2973001052 hasConceptScore W2973001052C13280743 @default.
• W2973001052 hasConceptScore W2973001052C134306372 @default.
• W2973001052 hasConceptScore W2973001052C152124472 @default.
• W2973001052 hasConceptScore W2973001052C153180895 @default.
• W2973001052 hasConceptScore W2973001052C154945302 @default.
• W2973001052 hasConceptScore W2973001052C185798385 @default.
• W2973001052 hasConceptScore W2973001052C205649164 @default.
• W2973001052 hasConceptScore W2973001052C2777984123 @default.
• W2973001052 hasConceptScore W2973001052C33923547 @default.
• W2973001052 hasConceptScore W2973001052C41008148 @default.
• W2973001052 hasConceptScore W2973001052C45347329 @default.
• W2973001052 hasConceptScore W2973001052C50644808 @default.
• W2973001052 hasConceptScore W2973001052C74193536 @default.
• W2973001052 hasConceptScore W2973001052C81363708 @default.
• W2973001052 hasFunder F4320321001 @default.
• W2973001052 hasFunder F4320326705 @default.
• W2973001052 hasIssue "8" @default.
• W2973001052 hasLocation W29730010521 @default.
• W2973001052 hasOpenAccess W2973001052 @default.
• W2973001052 hasPrimaryLocation W29730010521 @default.
• W2973001052 hasRelatedWork W2958745039 @default.
• W2973001052 hasRelatedWork W2963556241 @default.
• W2973001052 hasRelatedWork W3093612317 @default.
• W2973001052 hasRelatedWork W3159557112 @default.
• W2973001052 hasRelatedWork W3176983494 @default.

• next