CascadeC(NN): pushing the performance limits of quantisation in convolutional neural networks
File(s)
Accepted version
Author(s)
Kouris, Alexandros
Venieris, Stylianos I
Bouganis, Christos-Savvas
Type
Conference Paper
Abstract
This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference. A two-stage architecture tailored for any given CNN-FPGA pair is generated, consisting of a low-and high-precision unit in a cascade. A confidence evaluation unit is employed to identify misclassified cases from the excessively low-precision unit and forward them to the high-precision unit for re-processing. Experiments demonstrate that the proposed toolflow can achieve a performance boost up to 55% for VGG-16 and 48% for AlexNet over the baseline design for the same resource budget and accuracy, without the need of retraining the model or accessing the training data.
Date Issued
2018-12-06
Date Acceptance
2018-08-27
Citation
2018 28th International Conference on Field Programmable Logic and Applications (FPL), 2018, pp.155-162
ISSN
1946-1488
Publisher
IEEE
Start Page
155
End Page
162
Journal / Book Title
2018 28th International Conference on Field Programmable Logic and Applications (FPL)
Copyright Statement
© 2018 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.
Identifier
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000460538500027&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
Source
28th International Conference on Field Programmable Logic and Applications (FPL)
Subjects
Computer Science
Computer Science, Hardware & Architecture
Computer Science, Software Engineering
Science & Technology
Technology
Publication Status
Published
Start Date
2018-08-27
Finish Date
2018-08-28
Coverage Spatial
Dublin, IRELAND
Date Publish Online
2018-12-06