Title:
領域ベース敵対的学習での損傷転移方法
Document Type and Number:
Japanese Patent JP7394195
Kind Code:
B2
Abstract:
Example implementations involve systems and methods to create robust visual inspection datasets and models. The novel method learns and transfers damage representation from few samples to new images. The proposed method introduces a generative region-of-interest based adversarial network with the aim of learning a common damage representation and transferring it to an unseen image. The proposed approach shows the benefit of adding damage-region-based component, since existing methods fail to transfer the damages. The proposed method successfully generated images with variations in context and conditions to improve model generalization for small datasets.
Inventors:
Maria Teresa Gonzalez Diaz
Dipanjan Dipak Gosh
Mabubul Alam
Chetangupta
Eman Thi Hassan
Dipanjan Dipak Gosh
Mabubul Alam
Chetangupta
Eman Thi Hassan
Application Number:
JP2022172325A
Publication Date:
December 07, 2023
Filing Date:
October 27, 2022
Export Citation:
Assignee:
株式会社日立製作所
International Classes:
G06T7/00; G06N3/04; G06N3/08; G06V10/774; G06V10/82
Foreign References:
| KR1020210081077A | ||||
| CN112488984A |
Other References:
Shuanlong Niu et al.,Defect Image Sample Generation With GAN for Improving Defect Recognition,[online],2020年,https://ieeexplore.ieee.org/document/9000806
Attorney, Agent or Firm:
Patent Attorney Corporation Sunnext International Patent Office