논문 해외 국제전문학술지(SCI급) Exploiting Features with Split-and-Share Module
- 학술지 구분 국제전문학술지(SCI급)
- 게재년월 2022-01
- 저자명 최동걸
- 학술지명 ELECTRONICS
- 발행처명 MDPI
- 발행국가 해외
- 논문언어 외국어
- 전체저자수 6
홈페이지논문 초록 (Abstract)
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing convolutional blocks of the feature extractors, but less on the classifiers that exploit extracted features. In this work, we propose Split-and-Share Module (SSM), a classifier that splits a given feature into parts, which are partially shared by multiple sub-classifiers. Our intuition is that the more the features are shared, the more common they will become, and SSM can encourage such structural characteristics in the split features. SSM can be easily integrated into any architecture without bells and whistles. We have extensively validated the efficacy of SSM on ImageNet-1K classification task, and SSM has shown consistent and significant improvements over baseline architectures. In addition, we analyze the effect of SSM using the Grad-CAM visualization.