Structured Pruning for Deep Convolutional Neural Networks: A Survey

Page view(s)
9
Checked on Feb 10, 2025
Structured Pruning for Deep Convolutional Neural Networks: A Survey
Title:
Structured Pruning for Deep Convolutional Neural Networks: A Survey
Journal Title:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords:
Publication Date:
28 November 2023
Citation:
He, Y., & Xiao, L. (2024). Structured Pruning for Deep Convolutional Neural Networks: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 2900–2919. https://doi.org/10.1109/tpami.2023.3334614
Abstract:
The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has thus gained interest since it effectively lowers storage and computational costs. In contrast to weight pruning, which results in unstructured models, structured pruning provides the benefit of realistic acceleration by producing models that are friendly to hardware implementation. The special requirements of structured pruning have led to the discovery of numerous new challenges and the development of innovative solutions. This article surveys the recent progress towards structured pruning of deep CNNs. We summarize and compare the state-of-the-art structured pruning techniques with respect to filter ranking methods, regularization methods, dynamic execution, neural architecture search, the lottery ticket hypothesis, and the applications of pruning. While discussing structured pruning algorithms, we briefly introduce the unstructured pruning counterpart to emphasize their differences. Furthermore, we provide insights into potential research opportunities in the field of structured pruning. A curated list of neural network pruning papers can be found at: \url{https://github.com/he-y/Awesome-Pruning}. \red{A dedicated website offering a more interactive comparison of structured pruning methods can be found at: \url{https://huggingface.co/spaces/he-yang/Structured-Pruning-Survey}.
License type:
Publisher Copyright
Funding Info:
This work was supported in part by A*STAR Centre for Frontier AI Research (CFAR) and CFAR Internship Award and Research Excellence (CIARE)

This research / project is supported by the A*STAR Science and Engineering Research Council - Central Research Fund (CRF) Use-Inspired Basic Research
Grant Reference no. :

This research / project is supported by the Singapore Maritime Institute (SMI) - Maritime AI Research Programme
Grant Reference no. : SMI-2022-MTP-06
Description:
© 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.
ISSN:
0162-8828
2160-9292
1939-3539
Files uploaded:

File Size Format Action
structured-pruning-survey-camera-ready.pdf 1.61 MB PDF Open