FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2823177849> ?p ?o ?g. }

• W2823177849 abstract "In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains. The codes are available at https://github.com/IBM/BigLittleNet" @default.
• W2823177849 created "2018-07-19" @default.
• W2823177849 creator A5006044037 @default.
• W2823177849 creator A5025006492 @default.
• W2823177849 creator A5029989905 @default.
• W2823177849 creator A5052325109 @default.
• W2823177849 creator A5080417608 @default.
• W2823177849 date "2018-07-10" @default.
• W2823177849 modified "2023-09-25" @default.
• W2823177849 title "Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition" @default.
• W2823177849 cites W1556984771 @default.
• W2823177849 cites W1821462560 @default.
• W2823177849 cites W1861492603 @default.
• W2823177849 cites W1905829557 @default.
• W2823177849 cites W1919191429 @default.
• W2823177849 cites W2022508996 @default.
• W2823177849 cites W2031489346 @default.
• W2823177849 cites W2097117768 @default.
• W2823177849 cites W2104636679 @default.
• W2823177849 cites W2172166488 @default.
• W2823177849 cites W2182629226 @default.
• W2823177849 cites W2183341477 @default.
• W2823177849 cites W2194775991 @default.
• W2823177849 cites W2267635276 @default.
• W2823177849 cites W2307770531 @default.
• W2823177849 cites W2405920868 @default.
• W2823177849 cites W2463955103 @default.
• W2823177849 cites W2490270993 @default.
• W2823177849 cites W2533523411 @default.
• W2823177849 cites W2549139847 @default.
• W2823177849 cites W2559302184 @default.
• W2823177849 cites W2560533888 @default.
• W2823177849 cites W2565639579 @default.
• W2823177849 cites W2604998962 @default.
• W2823177849 cites W2605135468 @default.
• W2823177849 cites W2612983688 @default.
• W2823177849 cites W2739959771 @default.
• W2823177849 cites W2767421475 @default.
• W2823177849 cites W2768610172 @default.
• W2823177849 cites W2883780447 @default.
• W2823177849 cites W2884585870 @default.
• W2823177849 cites W2884751099 @default.
• W2823177849 cites W2899771611 @default.
• W2823177849 cites W2962737770 @default.
• W2823177849 cites W2962944050 @default.
• W2823177849 cites W2962965870 @default.
• W2823177849 cites W2963150697 @default.
• W2823177849 cites W2963163009 @default.
• W2823177849 cites W2963216524 @default.
• W2823177849 cites W2963263347 @default.
• W2823177849 cites W2963266252 @default.
• W2823177849 cites W2963393494 @default.
• W2823177849 cites W2963420686 @default.
• W2823177849 cites W2963446712 @default.
• W2823177849 cites W2963495494 @default.
• W2823177849 cites W2963821229 @default.
• W2823177849 cites W2964081403 @default.
• W2823177849 cites W2964081807 @default.
• W2823177849 cites W2964166828 @default.
• W2823177849 cites W2964227400 @default.
• W2823177849 cites W2964350391 @default.
• W2823177849 cites W300523764 @default.
• W2823177849 cites W8437397 @default.
• W2823177849 doi "https://doi.org/10.48550/arxiv.1807.03848" @default.
• W2823177849 hasPublicationYear "2018" @default.
• W2823177849 type Work @default.
• W2823177849 sameAs 2823177849 @default.
• W2823177849 citedByCount "0" @default.
• W2823177849 crossrefType "posted-content" @default.
• W2823177849 hasAuthorship W2823177849A5006044037 @default.
• W2823177849 hasAuthorship W2823177849A5025006492 @default.
• W2823177849 hasAuthorship W2823177849A5029989905 @default.
• W2823177849 hasAuthorship W2823177849A5052325109 @default.
• W2823177849 hasAuthorship W2823177849A5080417608 @default.
• W2823177849 hasBestOaLocation W28231778491 @default.
• W2823177849 hasConcept C11413529 @default.
• W2823177849 hasConcept C119857082 @default.
• W2823177849 hasConcept C134306372 @default.
• W2823177849 hasConcept C138885662 @default.
• W2823177849 hasConcept C153180895 @default.
• W2823177849 hasConcept C154945302 @default.
• W2823177849 hasConcept C173608175 @default.
• W2823177849 hasConcept C177148314 @default.
• W2823177849 hasConcept C17744445 @default.
• W2823177849 hasConcept C199539241 @default.
• W2823177849 hasConcept C2776359362 @default.
• W2823177849 hasConcept C2776401178 @default.
• W2823177849 hasConcept C28490314 @default.
• W2823177849 hasConcept C33923547 @default.
• W2823177849 hasConcept C3826847 @default.
• W2823177849 hasConcept C41008148 @default.
• W2823177849 hasConcept C41895202 @default.
• W2823177849 hasConcept C45374587 @default.
• W2823177849 hasConcept C52622490 @default.
• W2823177849 hasConcept C64876066 @default.
• W2823177849 hasConcept C774472 @default.
• W2823177849 hasConcept C81363708 @default.
• W2823177849 hasConcept C94625758 @default.
• W2823177849 hasConceptScore W2823177849C11413529 @default.
• W2823177849 hasConceptScore W2823177849C119857082 @default.

• next