모바일 메뉴 닫기
 

연구

Research & Laboratory

제목
세미나 [01/30] Towards Sub-4-bit Quantization of Optimized Mobile Networks
작성일
2020.01.29
작성자
전기전자공학부
게시글 내용

< BK21 플러스 BEST 정보기술 사업단 세미나 개최 안내 > 


개최일시 : 2020년 1월 30일 (목) 11:00 ~ 12:00

개최장소 : 제4공학관 D503호

세미나 제목 : Towards Sub-4-bit Quantization of Optimized Mobile Networks

내용 : 4-bit quantization of optimized mobile models such as MobileNet-v3 is challenging due to recently adopted architectural optimizations. According to our observation, it is mainly limited by activation instability incurred by weight quantization (AIWQ). In order to mitigate the effect of AIWQ, a novel training method called BN last (BLast) is proposed. In addition, a differentiable quantization method called DuQ is proposed that improves upon the state-of-the-art quantization method. Our experiments show that the proposed methods offer 4-bit weight/activation quantization of MobileNet-v3 on ImageNet at a negligible accuracy loss (0.916 %) from the full-precision top-1 accuracy.

 


강연자 성함&직함 / 소속 : 박은혁 연구원 / 서울대학교

초청자 : 전기전자공학과 교수 김한준