Title:
DEVICES, SYSTEMS, METHODS, AND MEDIA FOR DOMAIN ADAPTATION USING HYBRID LEARNING
Document Type and Number:
WIPO Patent Application WO/2023/040857
Kind Code:
A1
Abstract:
Devices, systems, methods, and media are for domain adaptation of a trained machine learning model using hybrid learning. A hybrid approach to domain adaptation is that combines aspects of discrepancy-based, adversarial, and reconstruction-based approaches to achieve an end-to-end trained model for performing a prediction task (such as semantic segmentation) on a sparsely labeled dataset in a target domain, by leveraging a richly-labeled dataset in the source domain. It may also provide a trained domain translation model for generating synthetic data samples in a first domain based on input data samples from a second domain.
Inventors:
CORRAL-SOTO EDUARDO (CA)
LIU BINGBING (CA)
LIU BINGBING (CA)
Application Number:
PCT/CN2022/118582
Publication Date:
March 23, 2023
Filing Date:
September 14, 2022
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
| US20200193269A1 | 2020-06-18 | |||
| US20170147944A1 | 2017-05-25 | |||
| US20210201152A1 | 2021-07-01 | |||
| US20210216818A1 | 2021-07-15 |
Download PDF: