Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885201213> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2885201213 abstract "In this work, we propose a multiplication-less deep convolution neural network, called BD-NET. As far as we know, BD-NET is the first to use binarized depthwise separable convolution block as the drop-in replacement of conventional spatial-convolution in deep convolution neural network (CNN). In BD-NET, the computation-expensive convolution operations (i.e. Multiplication and Accumulation) are converted into hardware-friendly Addition/Subtraction operations. In this work, we first investigate and analyze the performance of BD-NET in terms of accuracy, parameter size and computation cost, w.r.t various network configurations. Then, the experiment results show that our proposed BD-NET with binarized depthwise separable convolution can achieve even higher inference accuracy to its baseline CNN counterpart with full-precision conventional convolution layer on the CIFAR-10 dataset. From the perspective of hardware implementation, the convolution layer of BD-NET achieves up to 97.2%, 88.9%, and 99.4% reduction in terms of computation energy, memory usage, and chip area respectively." @default.
- W2885201213 created "2018-08-22" @default.
- W2885201213 creator A5030138469 @default.
- W2885201213 creator A5036755436 @default.
- W2885201213 creator A5047916979 @default.
- W2885201213 creator A5051680668 @default.
- W2885201213 date "2018-07-01" @default.
- W2885201213 modified "2023-09-23" @default.
- W2885201213 title "BD-NET: A Multiplication-Less DNN with Binarized Depthwise Separable Convolution" @default.
- W2885201213 cites W2194775991 @default.
- W2885201213 cites W2919115771 @default.
- W2885201213 doi "https://doi.org/10.1109/isvlsi.2018.00033" @default.
- W2885201213 hasPublicationYear "2018" @default.
- W2885201213 type Work @default.
- W2885201213 sameAs 2885201213 @default.
- W2885201213 citedByCount "3" @default.
- W2885201213 countsByYear W28852012132020 @default.
- W2885201213 countsByYear W28852012132021 @default.
- W2885201213 countsByYear W28852012132022 @default.
- W2885201213 crossrefType "proceedings-article" @default.
- W2885201213 hasAuthorship W2885201213A5030138469 @default.
- W2885201213 hasAuthorship W2885201213A5036755436 @default.
- W2885201213 hasAuthorship W2885201213A5047916979 @default.
- W2885201213 hasAuthorship W2885201213A5051680668 @default.
- W2885201213 hasConcept C11413529 @default.
- W2885201213 hasConcept C114614502 @default.
- W2885201213 hasConcept C134306372 @default.
- W2885201213 hasConcept C154945302 @default.
- W2885201213 hasConcept C2776214188 @default.
- W2885201213 hasConcept C2780595030 @default.
- W2885201213 hasConcept C33923547 @default.
- W2885201213 hasConcept C41008148 @default.
- W2885201213 hasConcept C45347329 @default.
- W2885201213 hasConcept C45374587 @default.
- W2885201213 hasConcept C50644808 @default.
- W2885201213 hasConcept C70710897 @default.
- W2885201213 hasConcept C81363708 @default.
- W2885201213 hasConceptScore W2885201213C11413529 @default.
- W2885201213 hasConceptScore W2885201213C114614502 @default.
- W2885201213 hasConceptScore W2885201213C134306372 @default.
- W2885201213 hasConceptScore W2885201213C154945302 @default.
- W2885201213 hasConceptScore W2885201213C2776214188 @default.
- W2885201213 hasConceptScore W2885201213C2780595030 @default.
- W2885201213 hasConceptScore W2885201213C33923547 @default.
- W2885201213 hasConceptScore W2885201213C41008148 @default.
- W2885201213 hasConceptScore W2885201213C45347329 @default.
- W2885201213 hasConceptScore W2885201213C45374587 @default.
- W2885201213 hasConceptScore W2885201213C50644808 @default.
- W2885201213 hasConceptScore W2885201213C70710897 @default.
- W2885201213 hasConceptScore W2885201213C81363708 @default.
- W2885201213 hasLocation W28852012131 @default.
- W2885201213 hasOpenAccess W2885201213 @default.
- W2885201213 hasPrimaryLocation W28852012131 @default.
- W2885201213 hasRelatedWork W2296411508 @default.
- W2885201213 hasRelatedWork W2513928851 @default.
- W2885201213 hasRelatedWork W2755240195 @default.
- W2885201213 hasRelatedWork W2810384904 @default.
- W2885201213 hasRelatedWork W2885201213 @default.
- W2885201213 hasRelatedWork W2953333557 @default.
- W2885201213 hasRelatedWork W3005273712 @default.
- W2885201213 hasRelatedWork W3107426390 @default.
- W2885201213 hasRelatedWork W4297812642 @default.
- W2885201213 hasRelatedWork W4312417841 @default.
- W2885201213 isParatext "false" @default.
- W2885201213 isRetracted "false" @default.
- W2885201213 magId "2885201213" @default.
- W2885201213 workType "article" @default.