ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술지 Implicit Semantic Data Augmentation for Hand Pose Estimation
Cited 2 time in scopus Download 77 time Share share facebook twitter linkedin kakaostory
서경은, 조현중, 최대웅, 박주덕
IEEE Access, v.10, pp.84680-84688
22IR4100, 인프라 센서 기반의 도로 상황 인지 고도화 기술 개발, 박주덕
Data augmentation is a well-known technique used for improving the generalization performance of modern neural networks. After the success of several traditional random data augmentation for images (including flipping, translation, or rotation), a recent surge of interest in implicit data augmentation techniques occurs to complement random data augmentation techniques. Implicit data augmentation augments training samples in feature space, rather than in pixel space, resulting in the generation of semantically meaningful data. Several techniques on implicit data augmentation have been introduced for classification tasks. However, few approaches have been introduced for regression tasks with continuous/structured labels, such as object pose estimation. Hence, we are motivated to propose a method for implicit semantic data augmentation for hand pose estimation. By considering semantic distances of hand poses, the proposed method implicitly generates extra training samples in feature space. We propose two additional techniques to improve the performance of this augmentation: metric learning and hand-dependent augmentation. Metric learning aims to learn feature representations to reflect the semantic distance of data. For hand pose estimation, the distribution of augmented hand poses can be regulated by managing the distribution of feature representations. Meanwhile, hand-dependent augmentation is specifically designed for hand pose estimation to prevent semantically meaningless hand poses from being generated (e.g., hands generated by simple interpolation between both hands). Further, we demonstrate the effectiveness of the proposed technique using two well-known hand pose datasets: STB and RHD.
KSP 제안 키워드
Augmentation techniques, Both hands, Data Augmentation, Feature representation, Feature space, Generalization performance, Hand pose estimation, Metric learning, Object Pose Estimation, Pixel space, Random data
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)