ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Where to Cut and Paste: Data Regularization with Selective Features
Cited 1 time in scopus Download 12 time Share share facebook twitter linkedin kakaostory
저자
김지연, 신익희, 이종률, 이용주
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1219-1221
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289404
협약과제
20HS3300, 부하분산과 능동적 적시 대응을 위한 빅데이터 엣지 분석 기술 개발, 이용주
초록
Deep convolutional neural networks are continually evolving through various effective training methods such as data augmentation. Among data augmentation methods, regional dropout or replacement strategies such as [3], [4], [5] have been proved effective in recognition and localization performance. However, such methods suffer from unintended content corruption like informative pixel loss. For example, cutting and pasting a random patch may consist of areas that are not important and even if a new cutout patch consists of informative pixels, it could be pasted at useful locations of input covering the interest of the object. Therefore, this operation can cause too much or meaningless regularization. Motivated by this, we propose a new data augmentation method strategy, called FocusMix, which exploits informative pixels based on proper sampling techniques. Through experiments, we analyzed and compared various data augmentation methods to provide improvements and effectiveness of FocusMix. Finally, we have shown that FocusMix results in improvements in performance compared to other data augmentation methods.
키워드
data augmentation, regional regularization
KSP 제안 키워드
Augmentation method, Convolution neural network(CNN), Data Augmentation, Deep convolutional neural networks, Effective training, Localization performance, sampling techniques, training method