Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387293271> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4387293271 abstract "Photonic computing promises faster and more energy-efficient deep neural network (DNN) inference than traditional digital hardware. Advances in photonic computing can have profound impacts on applications such as autonomous driving and defect detection that depend on fast, accurate and energy efficient execution of image segmentation models. In this paper, we investigate image segmentation on photonic accelerators to explore: a) the types of image segmentation DNN architectures that are best suited for photonic accelerators, and b) the throughput and energy efficiency of executing the different image segmentation models on photonic accelerators, along with the trade-offs involved therein. Specifically, we demonstrate that certain segmentation models exhibit negligible loss in accuracy (compared to digital float32 models) when executed on photonic accelerators, and explore the empirical reasoning for their robustness. We also discuss techniques for recovering accuracy in the case of models that do not perform well. Further, we compare throughput (inferences-per-second) and energy consumption estimates for different image segmentation workloads on photonic accelerators. We discuss the challenges and potential optimizations that can help improve the application of photonic accelerators to such computer vision tasks." @default.
- W4387293271 created "2023-10-03" @default.
- W4387293271 creator A5009879963 @default.
- W4387293271 creator A5024975994 @default.
- W4387293271 creator A5049242177 @default.
- W4387293271 creator A5056813998 @default.
- W4387293271 creator A5081939878 @default.
- W4387293271 creator A5084630487 @default.
- W4387293271 creator A5086794523 @default.
- W4387293271 creator A5092990883 @default.
- W4387293271 creator A5092990884 @default.
- W4387293271 date "2023-09-28" @default.
- W4387293271 modified "2023-10-06" @default.
- W4387293271 title "Photonic Accelerators for Image Segmentation in Autonomous Driving and Defect Detection" @default.
- W4387293271 doi "https://doi.org/10.48550/arxiv.2309.16783" @default.
- W4387293271 hasPublicationYear "2023" @default.
- W4387293271 type Work @default.
- W4387293271 citedByCount "0" @default.
- W4387293271 crossrefType "posted-content" @default.
- W4387293271 hasAuthorship W4387293271A5009879963 @default.
- W4387293271 hasAuthorship W4387293271A5024975994 @default.
- W4387293271 hasAuthorship W4387293271A5049242177 @default.
- W4387293271 hasAuthorship W4387293271A5056813998 @default.
- W4387293271 hasAuthorship W4387293271A5081939878 @default.
- W4387293271 hasAuthorship W4387293271A5084630487 @default.
- W4387293271 hasAuthorship W4387293271A5086794523 @default.
- W4387293271 hasAuthorship W4387293271A5092990883 @default.
- W4387293271 hasAuthorship W4387293271A5092990884 @default.
- W4387293271 hasBestOaLocation W43872932711 @default.
- W4387293271 hasConcept C104317684 @default.
- W4387293271 hasConcept C113775141 @default.
- W4387293271 hasConcept C120665830 @default.
- W4387293271 hasConcept C121332964 @default.
- W4387293271 hasConcept C124504099 @default.
- W4387293271 hasConcept C154945302 @default.
- W4387293271 hasConcept C185592680 @default.
- W4387293271 hasConcept C20788544 @default.
- W4387293271 hasConcept C2776214188 @default.
- W4387293271 hasConcept C31972630 @default.
- W4387293271 hasConcept C41008148 @default.
- W4387293271 hasConcept C55493867 @default.
- W4387293271 hasConcept C63479239 @default.
- W4387293271 hasConcept C89600930 @default.
- W4387293271 hasConceptScore W4387293271C104317684 @default.
- W4387293271 hasConceptScore W4387293271C113775141 @default.
- W4387293271 hasConceptScore W4387293271C120665830 @default.
- W4387293271 hasConceptScore W4387293271C121332964 @default.
- W4387293271 hasConceptScore W4387293271C124504099 @default.
- W4387293271 hasConceptScore W4387293271C154945302 @default.
- W4387293271 hasConceptScore W4387293271C185592680 @default.
- W4387293271 hasConceptScore W4387293271C20788544 @default.
- W4387293271 hasConceptScore W4387293271C2776214188 @default.
- W4387293271 hasConceptScore W4387293271C31972630 @default.
- W4387293271 hasConceptScore W4387293271C41008148 @default.
- W4387293271 hasConceptScore W4387293271C55493867 @default.
- W4387293271 hasConceptScore W4387293271C63479239 @default.
- W4387293271 hasConceptScore W4387293271C89600930 @default.
- W4387293271 hasLocation W43872932711 @default.
- W4387293271 hasOpenAccess W4387293271 @default.
- W4387293271 hasPrimaryLocation W43872932711 @default.
- W4387293271 hasRelatedWork W1522196789 @default.
- W4387293271 hasRelatedWork W2030563063 @default.
- W4387293271 hasRelatedWork W2045526782 @default.
- W4387293271 hasRelatedWork W2046243418 @default.
- W4387293271 hasRelatedWork W2055243143 @default.
- W4387293271 hasRelatedWork W2357796999 @default.
- W4387293271 hasRelatedWork W2741131631 @default.
- W4387293271 hasRelatedWork W4321636575 @default.
- W4387293271 hasRelatedWork W4379231730 @default.
- W4387293271 hasRelatedWork W595200200 @default.
- W4387293271 isParatext "false" @default.
- W4387293271 isRetracted "false" @default.
- W4387293271 workType "article" @default.