Publication:
Comparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimation

Simple item page
dc.contributor.authorLindamulage, A
dc.contributor.authorKodagoda, N
dc.contributor.authorReyal, S
dc.contributor.authorSamarasinghe, P
dc.contributor.authorYogarajah, P
dc.date.accessioned2023-01-24T02:57:29Z
dc.date.available2023-01-24T02:57:29Z
dc.date.issued2022-11-04
dc.description.abstractMagnitude-based pruning is a technique used to optimise deep learning models for edge inference. We have achieved over 75% model size reduction with a higher accuracy than the original multi-output regression model for head-pose estimationen_US
dc.identifier.citationA. Lindamulage, N. Kodagoda, S. Reyal, P. Samarasinghe and P. Yogarajah, "Comparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimation," TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON), Hong Kong, Hong Kong, 2022, pp. 1-6, doi: 10.1109/TENCON55691.2022.9977637.en_US
dc.identifier.doi10.1109/TENCON55691.2022.9977637en_US
dc.identifier.issn21593442
dc.identifier.urihttps://rda.sliit.lk/handle/123456789/3145
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofseriesIEEE Region 10 Annual International Conference, Proceedings/TENCON;Volume 2022
dc.subjectEdge Inferenceen_US
dc.subjectHead Pose estimationen_US
dc.subjectNetwork Pruningen_US
dc.subjectOptimisationen_US
dc.subjectQuantisationen_US
dc.subjectTensorFlowen_US
dc.titleComparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimationen_US
dc.typeArticleen_US
dspace.entity.typePublication

Files

Collections

Department of Information Technology