Progressive Gradient Pruning for Classification, Detection and DomainAdaptation release_u245y2qjenbkjk7upsolqsox4q

by Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Louis-Antoine Blais-Morin, Marco Pedersoli

Released as a article .

2020  

Abstract

Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing. Filter pruning techniques haverecently shown promising results for the compression andacceleration of convolutional NNs (CNNs). However, thesetechniques involve numerous steps and complex optimisa-tions because some only prune after training CNNs, whileothers prune from scratch during training by integratingsparsity constraints or modifying the loss function.In this paper we propose a new Progressive GradientPruning (PGP) technique for iterative filter pruning dur-ing training. In contrast to previous progressive pruningtechniques, it relies on a novel filter selection criterion thatmeasures the change in filter weights, uses a new hard andsoft pruning strategy and effectively adapts momentum ten-sors during the backward propagation pass. Experimentalresults obtained after training various CNNs on image datafor classification, object detection and domain adaptationbenchmarks indicate that the PGP technique can achievea better trade-off between classification accuracy and net-work (time and memory) complexity than PSFP and otherstate-of-the-art filter pruning techniques.
In text/plain format

Archived Files and Locations

application/pdf  455.5 kB
file_2wsdkn2xizbrhboonfpsk23hmu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-02-25
Version   v4
Language   en ?
arXiv  1906.08746v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 423880e4-127e-429b-b7d6-93dd9dc4d7df
API URL: JSON