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
|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). https://dx.doi.org/10.1109/DAC56929.2023.10247965||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 https://github.com/ntuliuteam/Teco.||URI:||https://hdl.handle.net/10356/167489||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: https://doi.org/10.1109/DAC56929.2023.10247965.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Conference Papers|
Updated on Sep 30, 2023
Updated on Sep 30, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.