ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Multiple flow‐based knowledge transfer via adversarial networks
Cited 4 time in scopus Share share facebook twitter linkedin kakaostory
Authors
D. Yeo, J.-H. Bae
Issue Date
2019-09
Citation
Electronics Letters, v.55, no.18, pp.989-992
ISSN
0013-5194
Publisher
IET
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1049/el.2019.1874
Abstract
The authors propose a new knowledge transfer method coupled with a generative adversarial network (GAN) when multiple-flow-based knowledge is considered in a teacher?뱒tudent framework using a residual network (ResNet). In this method, several independent discriminators adapting multilayer-perceptron-based structures were designed for flow-based knowledge transfer. The proposed GAN-based optimisation alternatively updates the multiple discriminators and a student ResNet such that the flow-based features of the student ResNet are generated as closely as possible to the real features of a teacher ResNet. The experiments demonstrate that the student ResNet trained using the proposed method more accurately captures the distribution of the flow-based teacher knowledge than the l2-distance-based training method. In addition, the proposed method provided better classification accuracy than the existing GAN-based knowledge transfer method.
KSP Keywords
Coupled with, Distance-based, Flow-based(FB), GaN-Based, Knowledge transfer, Residual Network, Transfer method, classification accuracy, generative adversarial network, training method