경량 딥러닝 모델의 초저정밀도 양자화를 위한 학습 방식의 개선
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김현승 | - |
dc.contributor.author | 김민수 | - |
dc.contributor.author | 최정욱 | - |
dc.date.accessioned | 2023-11-14T08:44:34Z | - |
dc.date.available | 2023-11-14T08:44:34Z | - |
dc.date.created | 2023-07-19 | - |
dc.date.issued | 2020-11 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192369 | - |
dc.description.abstract | Deep Learning Model Quantization is the most effective technique to make a model much lighter and cost efficient in terms of computation. Above many quantization algorithms, PROFIT[1] is a specialized algorithm for sub 4-bit mobile network quantization. But this method has sudden accuracy degradation in 2-bit width precision. In this paper, we propose a better training method to deal with this problem in 2-bit weight quantization. We adopt AIWQ, a metric for the activation’s instability induced by weight quantization [1] and make threshold value with this metric. Using threshold value, we stop training some quantized layers which have high sensitivity to weight quantization and fine-tune the rest of the quantized layers with different learning rate and scheduler. With this advanced training method, we improved 2-bit weight quantization accuracy of light deep learning models including EfficientNetB0 and MobilenetV2. | - |
dc.language | 한국어 | - |
dc.language.iso | ko | - |
dc.publisher | 대한전자공학회 | - |
dc.title | 경량 딥러닝 모델의 초저정밀도 양자화를 위한 학습 방식의 개선 | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | 최정욱 | - |
dc.identifier.bibliographicCitation | 2020년도 대한전자공학회 추계학술대회 논문집, pp.601 - 604 | - |
dc.relation.isPartOf | 2020년도 대한전자공학회 추계학술대회 논문집 | - |
dc.citation.title | 2020년도 대한전자공학회 추계학술대회 논문집 | - |
dc.citation.startPage | 601 | - |
dc.citation.endPage | 604 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 2 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.identifier.url | https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE10521871 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.