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

Asiri Lindamulage, Nuwan Kodagoda, Shyam Reyal, Pradeepa Samarasinghe, Pratheepan Yogarajah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Magnitude-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 estimation.
Original languageEnglish
Title of host publicationProceedings of TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)
ISBN (Electronic)978-1-6654-5095-9
ISBN (Print)978-1-6654-5096-6
Publication statusPublished (in print/issue) - 20 Dec 2022

Publication series

PublisherIEEE Control Society
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Bibliographical note

Funding Information:
VI. EXPERIMENTAL RESULTS AND CODES Experimental results and the model pruning code can be found at: VII. ACKNOWLEDGEMENT This research was supported by the Accelerating Higher Education Expansion and Development (AHEAD) Operation of the Ministry of Higher Education of Sri Lanka funded by the World Bank (

Publisher Copyright:
© 2022 IEEE.


  • Edge inference
  • Optimisation
  • Network Pruning
  • Quantisation
  • TensorFlow
  • Head Post estimation
  • Head Pose estimation
  • Edge Inference

Cite this