Imperial College London
Alternate

ProfessorChristos-SavvasBouganis

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Intelligent Digital Systems
 
 
 
//

Contact

 

+44 (0)20 7594 6144christos-savvas.bouganis Website

 
 
//

Location

 

904Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Bonato:2021:10.1016/j.asoc.2021.107316,
author = {Bonato, V and Bouganis, C-S},
doi = {10.1016/j.asoc.2021.107316},
journal = {Applied Soft Computing},
pages = {1--12},
title = {Class-specific early exit design methodology for convolutional neural networks.},
url = {http://dx.doi.org/10.1016/j.asoc.2021.107316},
volume = {107},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Convolutional Neural Network-based (CNN) inference is a demanding computational task where a longsequence of operations is applied to an input as dictated by the network topology. Optimisationsby data quantisation, data reuse, network pruning, and dedicated hardware architectures have astrong impact on reducing both energy consumption and hardware resource requirements, and onimproving inference latency. Implementing new applications from established models available fromboth academic and industrial worlds is common nowadays. Further optimisations by preserving modelarchitecture have been proposed via early exiting approaches, where additional exit points are includedin order to evaluate classifications of samples that produce feature maps with sufficient evidence tobe classified before reaching the final model exit. This paper proposes a methodology for designingearly-exit networks from a given baseline model aiming to improve the average latency for a targetedsubset class constrained by the original accuracy for all classes. Results demonstrate average timesaving in the order of 2.09× to 8.79× for dataset CIFAR10 and 15.00× to 20.71× for CIFAR100 forbaseline models ResNet-21, ResNet-110, Inceptionv3-159, and DenseNet-121.
AU  - Bonato,V
AU  - Bouganis,C-S
DO  - 10.1016/j.asoc.2021.107316
EP  - 12
PY  - 2021///
SN  - 1568-4946
SP  - 1
TI  - Class-specific early exit design methodology for convolutional neural networks.
T2  - Applied Soft Computing
UR  - http://dx.doi.org/10.1016/j.asoc.2021.107316
UR  - https://www.sciencedirect.com/science/article/pii/S1568494621002398
UR  - http://hdl.handle.net/10044/1/90316
VL  - 107
ER  -
Download