Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308236831> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4308236831 abstract "With the increase of depth and width, Deep Neural Network has got the best results in the computer vision, but its massive calculation has brought a heavy burden to IOT devices. To speed up the inference of DNN models, Branchynet creatively puts forward the early exit, which means that samples exit from shallow layers to reduce the calculation amount of the model. But Branchynet has some unnecessary intermediate calculations in the inference process. We propose a dispense mode to solve this problem, which can optimize the accuracy and latency of BranchyNet at the same time. The dispense mode directly determines the exit position of the sample in the multi-branch network according to the difficulty of the sample without intermediate trial errors. Under the same accuracy requirements, the inference speed is improved by 30%-50% compared with the cascade mode of Branchynet. Moreover, while further reducing redundant calculation, it provides a method for dynamic adjustment of accuracy. Thus, our framework can easily adjust the accuracy of the model to meet higher throughputs." @default.
- W4308236831 created "2022-11-09" @default.
- W4308236831 creator A5032416933 @default.
- W4308236831 creator A5052528809 @default.
- W4308236831 date "2022-10-16" @default.
- W4308236831 modified "2023-10-14" @default.
- W4308236831 title "Dispense Mode for Inference to Accelerate Branchynet" @default.
- W4308236831 cites W2567642374 @default.
- W4308236831 cites W2604319603 @default.
- W4308236831 cites W2950865323 @default.
- W4308236831 cites W2962677625 @default.
- W4308236831 cites W2963122961 @default.
- W4308236831 cites W2966950562 @default.
- W4308236831 cites W2979679572 @default.
- W4308236831 cites W3016208860 @default.
- W4308236831 cites W3049640275 @default.
- W4308236831 cites W3051231527 @default.
- W4308236831 cites W3092082681 @default.
- W4308236831 cites W4243928383 @default.
- W4308236831 doi "https://doi.org/10.1109/icip46576.2022.9897574" @default.
- W4308236831 hasPublicationYear "2022" @default.
- W4308236831 type Work @default.
- W4308236831 citedByCount "0" @default.
- W4308236831 crossrefType "proceedings-article" @default.
- W4308236831 hasAuthorship W4308236831A5032416933 @default.
- W4308236831 hasAuthorship W4308236831A5052528809 @default.
- W4308236831 hasConcept C10138342 @default.
- W4308236831 hasConcept C111919701 @default.
- W4308236831 hasConcept C11413529 @default.
- W4308236831 hasConcept C127413603 @default.
- W4308236831 hasConcept C154945302 @default.
- W4308236831 hasConcept C162324750 @default.
- W4308236831 hasConcept C185592680 @default.
- W4308236831 hasConcept C198082294 @default.
- W4308236831 hasConcept C198531522 @default.
- W4308236831 hasConcept C2776214188 @default.
- W4308236831 hasConcept C34146451 @default.
- W4308236831 hasConcept C41008148 @default.
- W4308236831 hasConcept C42360764 @default.
- W4308236831 hasConcept C43617362 @default.
- W4308236831 hasConcept C48677424 @default.
- W4308236831 hasConcept C50644808 @default.
- W4308236831 hasConcept C76155785 @default.
- W4308236831 hasConcept C82876162 @default.
- W4308236831 hasConcept C98045186 @default.
- W4308236831 hasConceptScore W4308236831C10138342 @default.
- W4308236831 hasConceptScore W4308236831C111919701 @default.
- W4308236831 hasConceptScore W4308236831C11413529 @default.
- W4308236831 hasConceptScore W4308236831C127413603 @default.
- W4308236831 hasConceptScore W4308236831C154945302 @default.
- W4308236831 hasConceptScore W4308236831C162324750 @default.
- W4308236831 hasConceptScore W4308236831C185592680 @default.
- W4308236831 hasConceptScore W4308236831C198082294 @default.
- W4308236831 hasConceptScore W4308236831C198531522 @default.
- W4308236831 hasConceptScore W4308236831C2776214188 @default.
- W4308236831 hasConceptScore W4308236831C34146451 @default.
- W4308236831 hasConceptScore W4308236831C41008148 @default.
- W4308236831 hasConceptScore W4308236831C42360764 @default.
- W4308236831 hasConceptScore W4308236831C43617362 @default.
- W4308236831 hasConceptScore W4308236831C48677424 @default.
- W4308236831 hasConceptScore W4308236831C50644808 @default.
- W4308236831 hasConceptScore W4308236831C76155785 @default.
- W4308236831 hasConceptScore W4308236831C82876162 @default.
- W4308236831 hasConceptScore W4308236831C98045186 @default.
- W4308236831 hasFunder F4320337504 @default.
- W4308236831 hasLocation W43082368311 @default.
- W4308236831 hasOpenAccess W4308236831 @default.
- W4308236831 hasPrimaryLocation W43082368311 @default.
- W4308236831 hasRelatedWork W1976100036 @default.
- W4308236831 hasRelatedWork W1987753576 @default.
- W4308236831 hasRelatedWork W2356237567 @default.
- W4308236831 hasRelatedWork W2386387936 @default.
- W4308236831 hasRelatedWork W3008625068 @default.
- W4308236831 hasRelatedWork W3128807919 @default.
- W4308236831 hasRelatedWork W3176411177 @default.
- W4308236831 hasRelatedWork W3213660063 @default.
- W4308236831 hasRelatedWork W4308081923 @default.
- W4308236831 hasRelatedWork W2779562428 @default.
- W4308236831 isParatext "false" @default.
- W4308236831 isRetracted "false" @default.
- W4308236831 workType "article" @default.