Paper Info
Title
BPNet - Branch-pruned conditional neural network for systematic time-accuracy tradeoff in DNN inference - work-in-progress.
Abstract
Recently, there have been attempts to execute the neural network conditionally with auxiliary classifiers allowing early termination depending on the difficulty of the input, which can reduce the execution time or energy consumption without any or with negligible accuracy decrease. However, these studies do not consider how many or where the auxiliary classifiers, or branches, should be added in a systematic fashion. In this paper, we propose Branch-pruned Conditional Neural Network (BPNet) and its methodology in which the time-accuracy tradeoff for the conditional neural network can be found systematically. We applied BPNet to SqueezeNet, ResNet-20, and VGG-16 with CIFAR-10 and 100. BPNet achieves on average 2.0X of speedups without any accuracy drop on average compared to the base network.
Year
DOI
Venue
2019
10.1145/3349567.3351721
CODES+ISSS
Keywords
Field
DocType
BPNet,base network,branch-pruned conditional neural network,auxiliary classifiers,execution time,SqueezeNet,ResNet-20,VGG-16,CIFAR-10,CIFAR-100
Computer science,Work in process,Inference,Parallel computing,Artificial intelligence,Artificial neural network
Conference
ISBN
Citations 
PageRank 
978-1-4503-6923-7
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Kyungchul Park100.68
Youngmin Yi228125.93