Title:
FEW-SHOT RADAR TARGET RECOGNITION METHOD BASED ON HIERARCHICAL META TRANSFER
Document Type and Number:
WIPO Patent Application WO/2024/082374
Kind Code:
A1
Abstract:
The present invention belongs to the technical field of target recognition, and particularly relates to a few-shot radar target recognition method based on hierarchical meta transfer. In the present invention, features are extracted on the basis of an attention mechanism and hierarchical deep knowledge transfer at a feature level, a sample level and a task level is performed in order to search for an embedding space, such that a sample is close to a category atom of targets of the same category and is away from a category atom of targets of other categories. At the feature level, a feature encoder based on the attention mechanism is designed and global domain-invariant representations of samples are fully mined, such that the problem of domain difference in data distribution of the samples is solved; at the sample level, an atom encoder is designed, and more stable category atoms are generated, such that the influence of outlier samples is avoided; and at the task level, a meta learner is designed, learning experience of training tasks is accumulated and is transferred to a new task, and the capability of cross-task knowledge transfer of a model is developed, such that target recognition based on meta transfer is realized. The target recognition method of the present invention is an intelligent target recognition method.
More Like This:
Inventors:
GUO XIANSHENG (CN)
ZHANG YUKUN (CN)
LI LIN (CN)
SI HAONAN (CN)
QIAN BOCHENG (CN)
ZHONG KE (CN)
HUANG JIAN (CN)
ZHANG YUKUN (CN)
LI LIN (CN)
SI HAONAN (CN)
QIAN BOCHENG (CN)
ZHONG KE (CN)
HUANG JIAN (CN)
Application Number:
PCT/CN2022/133980
Publication Date:
April 25, 2024
Filing Date:
November 24, 2022
Export Citation:
Assignee:
YANGTZE DELTA REGION INSTITUTE QUZHOU UNIV OF ELECTRONIC SCIENCE AND TECHNOLOGY OF CHINA (CN)
International Classes:
G06N20/10
Foreign References:
CN114488140A | 2022-05-13 | |||
CN112990334A | 2021-06-18 | |||
US20210003700A1 | 2021-01-07 | |||
CN114511739A | 2022-05-17 | |||
CN114492581A | 2022-05-13 | |||
CN115345322A | 2022-11-15 |
Attorney, Agent or Firm:
CHENGDU, DIANJING IP AGENCY (CN)
Download PDF: