Please use this identifier to cite or link to this item:
Title: Towards efficient convolutional neural network for embedded hardware via multi-dimensional pruning
Authors: Kong, Hao
Liu, Di
Luo, Xiangzhong
Huai, Shuo
Subramaniam, Ravi
Makaya, Christian
Lin, Qian
Liu, Weichen
Keywords: Engineering::Computer science and engineering
Issue Date: 2023
Source: Kong, H., Liu, D., Luo, X., Huai, S., Subramaniam, R., Makaya, C., Lin, Q. & Liu, W. (2023). Towards efficient convolutional neural network for embedded hardware via multi-dimensional pruning. 2023 60th ACM/IEEE Design Automation Conference (DAC).
Project: I1801E0028 
metadata.dc.contributor.conference: 2023 60th ACM/IEEE Design Automation Conference (DAC)
Abstract: In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available anonymously at
ISBN: 979-8-3503-2348-1
DOI: 10.1109/DAC56929.2023.10247965
Schools: School of Computer Science and Engineering 
Research Centres: HP-NTU Digital Manufacturing Corporate Lab
Rights: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
dac_9pt.pdfFinally submitted version731.05 kBAdobe PDFThumbnail

Page view(s)

Updated on Sep 30, 2023


Updated on Sep 30, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.