Ajou University repository

Two-stage architectural fine-tuning for neural architecture search in efficient transfer learningoa mark
  • Park, Soohyun ;
  • Son, Seok Bin ;
  • Lee, Youn Kyu ;
  • Jung, Soyi ;
  • Kim, Joongheon
Citations

SCOPUS

0

Citation Export

Publication Year
2023-12-01
Journal
Electronics Letters
Publisher
John Wiley and Sons Inc
Citation
Electronics Letters, Vol.59 No.24
Keyword
image processingneural net architectureneural nets
Mesh Keyword
Fine tuningHigh quality dataImages processingNET architectureNeural architecturesNeural net architectureNeural network applicationPractical useSearch costsTransfer learning
All Science Classification Codes (ASJC)
Electrical and Electronic Engineering
Abstract
In many deep neural network (DNN) applications, the difficulty of gathering high-quality data in industry fields hinders the practical use of DNN. Thus, the concept of transfer learning (TL) has emerged, which leverages the pretrained knowledge of the DNN which was built based on large-scale datasets. For this TL objective, this paper suggests two-stage architectural fine-tuning for reducing the costs and time while exploring the most efficient DNN model, inspired by neural architecture search (NAS). The first stage is mutation, which reduces the search costs using a priori architectural information. Moreover, the next stage is early-stopping, which reduces NAS costs by terminating the search process in the middle of computation. The data-intensive experimental results verify that the proposed method outperforms benchmarks.
ISSN
1350-911X
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/33853
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85180133284&origin=inward
DOI
https://doi.org/2-s2.0-85180133284
Journal URL
https://ietresearch.onlinelibrary.wiley.com/loi/1350911x
Type
Article
Funding
This work was supported in part by the National Research Foundation of Korea (NRF\u2010Korea) under Grant and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant through the Korea Government [Ministry of Science and Information and Communications Technology (MSIT)], Intelligent 6G Wireless Access System, under Grant.
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Jung, Soyi Image
Jung, Soyi정소이
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.