Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand segmentation. Here, we focus on appearance gaps for hand regions and bac...

Full description

Bibliographic Details
Main Authors: Takehiko Ohkawa, Takuma Yagi, Atsushi Hashimoto, Yoshitaka Ushiku, Yoichi Sato
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Domain adaptation
first-person vision
semantic segmentation
Online Access:https://ieeexplore.ieee.org/document/9469781/

Internet

https://ieeexplore.ieee.org/document/9469781/

Similar Items