Matches in SemOpenAlex for { <https://semopenalex.org/work/W2550403740> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2550403740 abstract "In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision. However, DNN-based methods are both computational-intensive and resource-consuming, which hinders the application of these methods on embedded systems like smart phones. To alleviate this problem, we introduce a novel Fixed-point Factorized Networks (FFN) for pretrained models to reduce the computational complexity as well as the storage requirement of networks. The resulting networks have only weights of -1, 0 and 1, which significantly eliminates the most resource-consuming multiply-accumulate operations (MACs). Extensive experiments on large-scale ImageNet classification task show the proposed FFN only requires one-thousandth of multiply operations with comparable accuracy." @default.
- W2550403740 created "2016-11-30" @default.
- W2550403740 creator A5000727470 @default.
- W2550403740 creator A5079244166 @default.
- W2550403740 date "2017-07-01" @default.
- W2550403740 modified "2023-10-14" @default.
- W2550403740 title "Fixed-Point Factorized Networks" @default.
- W2550403740 cites W2013305145 @default.
- W2550403740 cites W2080051508 @default.
- W2550403740 cites W2117539524 @default.
- W2550403740 cites W2155893237 @default.
- W2550403740 cites W2194775991 @default.
- W2550403740 cites W2233116163 @default.
- W2550403740 cites W2525098248 @default.
- W2550403740 doi "https://doi.org/10.1109/cvpr.2017.422" @default.
- W2550403740 hasPublicationYear "2017" @default.
- W2550403740 type Work @default.
- W2550403740 sameAs 2550403740 @default.
- W2550403740 citedByCount "36" @default.
- W2550403740 countsByYear W25504037402017 @default.
- W2550403740 countsByYear W25504037402018 @default.
- W2550403740 countsByYear W25504037402019 @default.
- W2550403740 countsByYear W25504037402020 @default.
- W2550403740 countsByYear W25504037402021 @default.
- W2550403740 countsByYear W25504037402022 @default.
- W2550403740 countsByYear W25504037402023 @default.
- W2550403740 crossrefType "proceedings-article" @default.
- W2550403740 hasAuthorship W2550403740A5000727470 @default.
- W2550403740 hasAuthorship W2550403740A5079244166 @default.
- W2550403740 hasBestOaLocation W25504037402 @default.
- W2550403740 hasConcept C11413529 @default.
- W2550403740 hasConcept C119857082 @default.
- W2550403740 hasConcept C120314980 @default.
- W2550403740 hasConcept C127964446 @default.
- W2550403740 hasConcept C154945302 @default.
- W2550403740 hasConcept C159985019 @default.
- W2550403740 hasConcept C162324750 @default.
- W2550403740 hasConcept C179799912 @default.
- W2550403740 hasConcept C187736073 @default.
- W2550403740 hasConcept C192562407 @default.
- W2550403740 hasConcept C204323151 @default.
- W2550403740 hasConcept C206345919 @default.
- W2550403740 hasConcept C2524010 @default.
- W2550403740 hasConcept C2780451532 @default.
- W2550403740 hasConcept C28719098 @default.
- W2550403740 hasConcept C2984842247 @default.
- W2550403740 hasConcept C31258907 @default.
- W2550403740 hasConcept C33923547 @default.
- W2550403740 hasConcept C41008148 @default.
- W2550403740 hasConcept C50644808 @default.
- W2550403740 hasConcept C80444323 @default.
- W2550403740 hasConceptScore W2550403740C11413529 @default.
- W2550403740 hasConceptScore W2550403740C119857082 @default.
- W2550403740 hasConceptScore W2550403740C120314980 @default.
- W2550403740 hasConceptScore W2550403740C127964446 @default.
- W2550403740 hasConceptScore W2550403740C154945302 @default.
- W2550403740 hasConceptScore W2550403740C159985019 @default.
- W2550403740 hasConceptScore W2550403740C162324750 @default.
- W2550403740 hasConceptScore W2550403740C179799912 @default.
- W2550403740 hasConceptScore W2550403740C187736073 @default.
- W2550403740 hasConceptScore W2550403740C192562407 @default.
- W2550403740 hasConceptScore W2550403740C204323151 @default.
- W2550403740 hasConceptScore W2550403740C206345919 @default.
- W2550403740 hasConceptScore W2550403740C2524010 @default.
- W2550403740 hasConceptScore W2550403740C2780451532 @default.
- W2550403740 hasConceptScore W2550403740C28719098 @default.
- W2550403740 hasConceptScore W2550403740C2984842247 @default.
- W2550403740 hasConceptScore W2550403740C31258907 @default.
- W2550403740 hasConceptScore W2550403740C33923547 @default.
- W2550403740 hasConceptScore W2550403740C41008148 @default.
- W2550403740 hasConceptScore W2550403740C50644808 @default.
- W2550403740 hasConceptScore W2550403740C80444323 @default.
- W2550403740 hasLocation W25504037401 @default.
- W2550403740 hasLocation W25504037402 @default.
- W2550403740 hasOpenAccess W2550403740 @default.
- W2550403740 hasPrimaryLocation W25504037401 @default.
- W2550403740 hasRelatedWork W1485045889 @default.
- W2550403740 hasRelatedWork W1535667946 @default.
- W2550403740 hasRelatedWork W1576482347 @default.
- W2550403740 hasRelatedWork W2045719484 @default.
- W2550403740 hasRelatedWork W2159813516 @default.
- W2550403740 hasRelatedWork W2613818397 @default.
- W2550403740 hasRelatedWork W3159171600 @default.
- W2550403740 hasRelatedWork W4243722973 @default.
- W2550403740 hasRelatedWork W4289446326 @default.
- W2550403740 hasRelatedWork W2145131298 @default.
- W2550403740 isParatext "false" @default.
- W2550403740 isRetracted "false" @default.
- W2550403740 magId "2550403740" @default.
- W2550403740 workType "article" @default.