ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Does Identity Mapping Really Help in ResNet?
Cited 0 time in scopus Download 10 time Share share facebook twitter linkedin kakaostory
저자
이유경, 이동환, 최재훈, 유장희, 이승익
발행일
202110
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1077-1080
DOI
https://dx.doi.org/10.1109/ICTC52510.2021.9621166
협약과제
21HR3900, 심혈관질환을 위한 인공지능 주치의 기술 개발, 김승환
초록
ResNet proposed residual learning using skip connections that perform identity mapping. However, as shown in the study [1], identity mappings for skip connections may not be the optimal or at least not the only way to get a good performance in ResNet. In this paper, we explore various types of skip connections, including shortcuts with or without identity mapping, to see their effects on the performance of ResNet and provide a comparison of the various methods. Our extensive experiments suggest that the use of identity shortcuts is the most appropriate than other methods in terms of model simplicity and performance.
KSP 제안 키워드
Identity mapping, residual learning, skip connections