English

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

Computer Vision and Pattern Recognition 2023-02-02 v1 Artificial Intelligence
Authors: Asiri Lindamulage , Nuwan Kodagoda , Shyam Reyal , Pradeepa Samarasinghe , Pratheepan Yogarajah
View on arXiv ↗ PDF ↗ DOI ↗

Abstract

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.

Keywords

network pruning model compression neural network training

Cite

@article{arxiv.2302.00592,
  title  = {Comparative Study of Parameter Selection for Enhanced Edge Inference for a Multi-Output Regression model for Head Pose Estimation},
  author = {Asiri Lindamulage and Nuwan Kodagoda and Shyam Reyal and Pradeepa Samarasinghe and Pratheepan Yogarajah},
  journal= {arXiv preprint arXiv:2302.00592},
  year   = {2023}
}

Comments

Conference:- in TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)

Related papers

View all related →
Computer Vision and Pattern Recognition · Computer Science
Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge
Aditya Rajagopal, Christos-Savvas Bouganis
2020-06-18
Computer Vision and Pattern Recognition · Computer Science
Differentiable Transportation Pruning
Yunqiang Li, Jan C. van Gemert, Torsten Hoefler, Bert Moons +2
2023-08-01
Computer Vision and Pattern Recognition · Computer Science
Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning
Athul Shibu, Abhishek Kumar, Heechul Jung, Dong-Gyu Lee
2023-01-27
Machine Learning · Computer Science
Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge
Alexandre Broggi, Nathaniel Bastian, Lance Fiondella, Gokhan Kul
2025-05-21
Machine Learning · Computer Science
Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning
Sejun Park, Jaeho Lee, Sangwoo Mo, Jinwoo Shin
2020-02-17
Machine Learning · Computer Science
Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
Jiayi Liu, Samarth Tripathi, Unmesh Kurup, Mohak Shah
2020-05-12
Machine Learning · Computer Science
Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks
Beatrice Alessandra Motetti, Matteo Risso, Alessio Burrello, Enrico Macii +2
2024-09-25
Machine Learning · Computer Science
Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks
Samer Francy, Raghubir Singh
2024-09-05
Neural and Evolutionary Computing · Computer Science
A Framework For Pruning Deep Neural Networks Using Energy-Based Models
Hojjat Salehinejad, Shahrokh Valaee
2021-03-01
Machine Learning · Computer Science
Statistical Mechanical Analysis of Neural Network Pruning
Rupam Acharyya, Ankani Chattoraj, Boyu Zhang, Shouman Das +1
2021-06-14
Machine Learning · Computer Science
Neural Language Model Pruning for Automatic Speech Recognition
Leonardo Emili, Thiago Fraga-Silva, Ernest Pusateri, Markus Nußbaum-Thom +1
2023-10-06
Computation and Language · Computer Science
Movement Pruning: Adaptive Sparsity by Fine-Tuning
Victor Sanh, Thomas Wolf, Alexander M. Rush
2020-10-26
Machine Learning · Computer Science
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
Lucas Liebenwein, Cenk Baykal, Brandon Carter, David Gifford +1
2021-03-05
Computer Vision and Pattern Recognition · Computer Science
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
Nathan Hubens, Matei Mancas, Bernard Gosselin, Marius Preda +1
2021-12-16
Machine Learning · Statistics
To prune, or not to prune: exploring the efficacy of pruning for model compression
Michael Zhu, Suyog Gupta
2017-11-15
Image and Video Processing · Electrical Eng. & Systems
Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
Chicago Y. Park, Weijie Gan, Zihao Zou, Yuyang Hu +2
2025-04-04
Machine Learning · Computer Science
Elimination-compensation pruning for fully-connected neural networks
Enrico Ballini, Luca Muscarnera, Alessio Fumagalli, Anna Scotti +1
2026-02-25
Neural and Evolutionary Computing · Computer Science
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
Xin Dong, Shangyu Chen, Sinno Jialin Pan
2019-10-02
Machine Learning · Computer Science
Confident magnitude-based neural network pruning
Joaquin Alvarez
2024-08-12
Machine Learning · Computer Science
Magnitude and Uncertainty Pruning Criterion for Neural Networks
Vinnie Ko, Stefan Oehmcke, Fabian Gieseke
2019-12-11
Computer Vision and Pattern Recognition · Computer Science
Pruning Convolutional Neural Networks for Image Instance Retrieval
Gaurav Manek, Jie Lin, Vijay Chandrasekhar, Lingyu Duan +3
2017-07-19
Machine Learning · Computer Science
Detecting Dead Weights and Units in Neural Networks
Utku Evci
2018-06-19
Machine Learning · Computer Science
Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
Bailey J. Eccles, Leon Wong, Blesson Varghese
2025-04-09
Machine Learning · Computer Science
Effective Layer Pruning Through Similarity Metric Perspective
Ian Pons, Bruno Yamamoto, Anna H. Reali Costa, Artur Jordao
2024-11-05
Computer Vision and Pattern Recognition · Computer Science
Block Pruning for Enhanced Efficiency in Convolutional Neural Networks
Cheng-En Wu, Azadeh Davoodi, Yu Hen Hu
2024-01-17
R2 v1 2026-06-28T08:29:19.744Z