상세정보
학술대회
Does Identity Mapping Really Help in ResNet?
- 발행일
- 202110
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2021, pp.1077-1080
- 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