FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912563840> ?p ?o ?g. }

• W2912563840 abstract "A promising way to deploy Artificial Intelligence (AI)-based services on mobile devices is to run a part of the AI model (a deep neural network) on the mobile itself, and the rest in the cloud. This is sometimes referred to as collaborative intelligence. In this framework, intermediate features from the deep network need to be transmitted to the cloud for further processing. We study the case where such features are used for multiple purposes in the cloud (multi-tasking) and where they need to be compressible in order to allow efficient transmission to the cloud. To this end, we introduce a new loss function that encourages feature compressibility while improving system performance on multiple tasks. Experimental results show that with the compression-friendly loss, one can achieve around 20% bitrate reduction without sacrificing the performance on several vision-related tasks." @default.
• W2912563840 created "2019-02-21" @default.
• W2912563840 creator A5012187461 @default.
• W2912563840 creator A5076084094 @default.
• W2912563840 date "2019-02-14" @default.
• W2912563840 modified "2023-09-27" @default.
• W2912563840 title "Multi-task learning with compressible features for Collaborative Intelligence" @default.
• W2912563840 cites W1905829557 @default.
• W2912563840 cites W2101700394 @default.
• W2912563840 cites W2138163228 @default.
• W2912563840 cites W2194775991 @default.
• W2912563840 cites W2267126114 @default.
• W2912563840 cites W2276329208 @default.
• W2912563840 cites W2340897893 @default.
• W2912563840 cites W2552465432 @default.
• W2912563840 cites W2559975580 @default.
• W2912563840 cites W2562137921 @default.
• W2912563840 cites W2604392022 @default.
• W2912563840 cites W2605258629 @default.
• W2912563840 cites W2783569857 @default.
• W2912563840 cites W2803451246 @default.
• W2912563840 cites W2887096644 @default.
• W2912563840 cites W2891178669 @default.
• W2912563840 cites W2895432151 @default.
• W2912563840 cites W2899771611 @default.
• W2912563840 cites W2962790536 @default.
• W2912563840 cites W2962891349 @default.
• W2912563840 cites W2963377935 @default.
• W2912563840 cites W2963636093 @default.
• W2912563840 cites W2963677766 @default.
• W2912563840 cites W2963770864 @default.
• W2912563840 cites W2964121744 @default.
• W2912563840 cites W645922050 @default.
• W2912563840 hasPublicationYear "2019" @default.
• W2912563840 type Work @default.
• W2912563840 sameAs 2912563840 @default.
• W2912563840 citedByCount "2" @default.
• W2912563840 countsByYear W29125638402020 @default.
• W2912563840 countsByYear W29125638402021 @default.
• W2912563840 crossrefType "posted-content" @default.
• W2912563840 hasAuthorship W2912563840A5012187461 @default.
• W2912563840 hasAuthorship W2912563840A5076084094 @default.
• W2912563840 hasConcept C108583219 @default.
• W2912563840 hasConcept C111335779 @default.
• W2912563840 hasConcept C111919701 @default.
• W2912563840 hasConcept C120314980 @default.
• W2912563840 hasConcept C127413603 @default.
• W2912563840 hasConcept C138885662 @default.
• W2912563840 hasConcept C146978453 @default.
• W2912563840 hasConcept C154945302 @default.
• W2912563840 hasConcept C186967261 @default.
• W2912563840 hasConcept C201995342 @default.
• W2912563840 hasConcept C2524010 @default.
• W2912563840 hasConcept C2776401178 @default.
• W2912563840 hasConcept C2780451532 @default.
• W2912563840 hasConcept C33923547 @default.
• W2912563840 hasConcept C41008148 @default.
• W2912563840 hasConcept C41895202 @default.
• W2912563840 hasConcept C50644808 @default.
• W2912563840 hasConcept C79974875 @default.
• W2912563840 hasConcept C84655787 @default.
• W2912563840 hasConceptScore W2912563840C108583219 @default.
• W2912563840 hasConceptScore W2912563840C111335779 @default.
• W2912563840 hasConceptScore W2912563840C111919701 @default.
• W2912563840 hasConceptScore W2912563840C120314980 @default.
• W2912563840 hasConceptScore W2912563840C127413603 @default.
• W2912563840 hasConceptScore W2912563840C138885662 @default.
• W2912563840 hasConceptScore W2912563840C146978453 @default.
• W2912563840 hasConceptScore W2912563840C154945302 @default.
• W2912563840 hasConceptScore W2912563840C186967261 @default.
• W2912563840 hasConceptScore W2912563840C201995342 @default.
• W2912563840 hasConceptScore W2912563840C2524010 @default.
• W2912563840 hasConceptScore W2912563840C2776401178 @default.
• W2912563840 hasConceptScore W2912563840C2780451532 @default.
• W2912563840 hasConceptScore W2912563840C33923547 @default.
• W2912563840 hasConceptScore W2912563840C41008148 @default.
• W2912563840 hasConceptScore W2912563840C41895202 @default.
• W2912563840 hasConceptScore W2912563840C50644808 @default.
• W2912563840 hasConceptScore W2912563840C79974875 @default.
• W2912563840 hasConceptScore W2912563840C84655787 @default.
• W2912563840 hasLocation W29125638401 @default.
• W2912563840 hasOpenAccess W2912563840 @default.
• W2912563840 hasPrimaryLocation W29125638401 @default.
• W2912563840 hasRelatedWork W2121107042 @default.
• W2912563840 hasRelatedWork W2603618203 @default.
• W2912563840 hasRelatedWork W2807214292 @default.
• W2912563840 hasRelatedWork W2808973872 @default.
• W2912563840 hasRelatedWork W2885996416 @default.
• W2912563840 hasRelatedWork W2910908473 @default.
• W2912563840 hasRelatedWork W2924431334 @default.
• W2912563840 hasRelatedWork W2945673979 @default.
• W2912563840 hasRelatedWork W2946069507 @default.
• W2912563840 hasRelatedWork W2970003075 @default.
• W2912563840 hasRelatedWork W3002974274 @default.
• W2912563840 hasRelatedWork W3006314838 @default.
• W2912563840 hasRelatedWork W3012986730 @default.
• W2912563840 hasRelatedWork W3032528071 @default.
• W2912563840 hasRelatedWork W3044749595 @default.
• W2912563840 hasRelatedWork W3048959573 @default.
• W2912563840 hasRelatedWork W3080303811 @default.

• next