Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220807708> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4220807708 endingPage "29" @default.
- W4220807708 startingPage "1" @default.
- W4220807708 abstract "Real-time machine vision applications running on resource-constrained embedded systems face challenges for maintaining performance. An especially challenging scenario arises when multiple applications execute at the same time, creating contention for the computational resources of the system. This contention results in increase in inference delay of the machine vision applications, which can be unacceptable for time-critical tasks. To address this challenge, we propose an adaptive model selection framework that mitigates the impact of system contention and prevents unexpected increases in inference delay by trading off the application accuracy minimally. The framework has two parts, which are performed pre-deployment and at runtime. The pre-deployment part profiles the system for contention in a black-box manner and produces a model set that is specifically optimized for the contention levels observed in the system. The runtime part predicts the inference delays of each model considering the system contention and selects the best model according to the predictions for each frame. Compared to a fixed individual model with similar accuracy, our framework improves the performance by significantly reducing the inference delay violations against a specified threshold. We implement our framework on the Nvidia Jetson TX2 platform and show that our approach achieves greater than 20% reductions in delay violations over the individual baseline models." @default.
- W4220807708 created "2022-04-03" @default.
- W4220807708 creator A5017823328 @default.
- W4220807708 creator A5025308099 @default.
- W4220807708 creator A5065766721 @default.
- W4220807708 creator A5087729884 @default.
- W4220807708 date "2022-09-30" @default.
- W4220807708 modified "2023-10-04" @default.
- W4220807708 title "Contention Grading and Adaptive Model Selection for Machine Vision in Embedded Systems" @default.
- W4220807708 cites W1595781246 @default.
- W4220807708 cites W2117539524 @default.
- W4220807708 cites W2183341477 @default.
- W4220807708 cites W2300242332 @default.
- W4220807708 cites W2302255633 @default.
- W4220807708 cites W2797932837 @default.
- W4220807708 cites W2949736877 @default.
- W4220807708 cites W2962677625 @default.
- W4220807708 cites W2963125010 @default.
- W4220807708 cites W2963163009 @default.
- W4220807708 cites W2963446712 @default.
- W4220807708 cites W2964081807 @default.
- W4220807708 cites W2964233199 @default.
- W4220807708 cites W2979810270 @default.
- W4220807708 cites W2981698279 @default.
- W4220807708 cites W3045897451 @default.
- W4220807708 cites W3106250896 @default.
- W4220807708 cites W3107819843 @default.
- W4220807708 cites W3108652056 @default.
- W4220807708 cites W3114386910 @default.
- W4220807708 cites W3135991645 @default.
- W4220807708 cites W3137147200 @default.
- W4220807708 cites W3173385564 @default.
- W4220807708 cites W4243928383 @default.
- W4220807708 doi "https://doi.org/10.1145/3520134" @default.
- W4220807708 hasPublicationYear "2022" @default.
- W4220807708 type Work @default.
- W4220807708 citedByCount "5" @default.
- W4220807708 countsByYear W42208077082022 @default.
- W4220807708 countsByYear W42208077082023 @default.
- W4220807708 crossrefType "journal-article" @default.
- W4220807708 hasAuthorship W4220807708A5017823328 @default.
- W4220807708 hasAuthorship W4220807708A5025308099 @default.
- W4220807708 hasAuthorship W4220807708A5065766721 @default.
- W4220807708 hasAuthorship W4220807708A5087729884 @default.
- W4220807708 hasBestOaLocation W42208077081 @default.
- W4220807708 hasConcept C105339364 @default.
- W4220807708 hasConcept C115903868 @default.
- W4220807708 hasConcept C120314980 @default.
- W4220807708 hasConcept C126042441 @default.
- W4220807708 hasConcept C154945302 @default.
- W4220807708 hasConcept C177264268 @default.
- W4220807708 hasConcept C199360897 @default.
- W4220807708 hasConcept C2776214188 @default.
- W4220807708 hasConcept C41008148 @default.
- W4220807708 hasConcept C76155785 @default.
- W4220807708 hasConcept C79403827 @default.
- W4220807708 hasConceptScore W4220807708C105339364 @default.
- W4220807708 hasConceptScore W4220807708C115903868 @default.
- W4220807708 hasConceptScore W4220807708C120314980 @default.
- W4220807708 hasConceptScore W4220807708C126042441 @default.
- W4220807708 hasConceptScore W4220807708C154945302 @default.
- W4220807708 hasConceptScore W4220807708C177264268 @default.
- W4220807708 hasConceptScore W4220807708C199360897 @default.
- W4220807708 hasConceptScore W4220807708C2776214188 @default.
- W4220807708 hasConceptScore W4220807708C41008148 @default.
- W4220807708 hasConceptScore W4220807708C76155785 @default.
- W4220807708 hasConceptScore W4220807708C79403827 @default.
- W4220807708 hasFunder F4320332180 @default.
- W4220807708 hasIssue "5" @default.
- W4220807708 hasLocation W42208077081 @default.
- W4220807708 hasOpenAccess W4220807708 @default.
- W4220807708 hasPrimaryLocation W42208077081 @default.
- W4220807708 hasRelatedWork W1485627940 @default.
- W4220807708 hasRelatedWork W1596201972 @default.
- W4220807708 hasRelatedWork W1969481115 @default.
- W4220807708 hasRelatedWork W1998320603 @default.
- W4220807708 hasRelatedWork W2021850411 @default.
- W4220807708 hasRelatedWork W2160425906 @default.
- W4220807708 hasRelatedWork W2369067071 @default.
- W4220807708 hasRelatedWork W2373012867 @default.
- W4220807708 hasRelatedWork W2373884999 @default.
- W4220807708 hasRelatedWork W4312263439 @default.
- W4220807708 hasVolume "21" @default.
- W4220807708 isParatext "false" @default.
- W4220807708 isRetracted "false" @default.
- W4220807708 workType "article" @default.