Title:
LABEL GENERATION METHOD, MODEL GENERATION METHOD, LABEL GENERATION DEVICE, LABEL GENERATION PROGRAM, MODEL GENERATION DEVICE, AND MODEL GENERATION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/032665
Kind Code:
A1
Abstract:
A label generation method according to one aspect of the present invention prepares a first inference model trained on a first dataset obtained from a source domain, and a second inference model trained on a second dataset including second training data generated by adding a disturbance to first training data, and generates a third correct label for third training data, on the basis of a consensus of the prepared trained first inference model and second inference model.
Inventors:
OHKAWA TAKEHIKO (JP)
HASHIMOTO ATSUSHI (JP)
USHIKU YOSHITAKA (JP)
SATO YOICHI (JP)
YAGI TAKUMA (JP)
HASHIMOTO ATSUSHI (JP)
USHIKU YOSHITAKA (JP)
SATO YOICHI (JP)
YAGI TAKUMA (JP)
Application Number:
PCT/JP2022/031009
Publication Date:
March 09, 2023
Filing Date:
August 17, 2022
Export Citation:
Assignee:
OMRON TATEISI ELECTRONICS CO (JP)
UNIV TOKYO (JP)
UNIV TOKYO (JP)
International Classes:
G06N20/00; G06T7/00
Foreign References:
| JP2020170738A | 2020-10-15 | |||
| US20210056718A1 | 2021-02-25 |
Other References:
OHKAWA TAKEHIKO, YAGI TAKUMA, HASHIMOTO ATSUSHI, USHIKU YOSHITAKA, SATO YOICHI: "Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation", ARXIV.ORG, vol. 9, 11 July 2021 (2021-07-11), pages 94644 - 94655, XP093041276, DOI: 10.1109/ACCESS.2021.3094052
Attorney, Agent or Firm:
TACHIBANA, Kenji et al. (JP)
Download PDF: