The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 20, 2023

Filed:

Sep. 22, 2022
Applicant:

National University of Defense Technology, Hunan, CN;

Inventors:

Yanming Guo, Hunan, CN;

Jian Li, Hunan, CN;

Songyang Lao, Hunan, CN;

Liang Bai, Hunan, CN;

Yingmei Wei, Hunan, CN;

Yulun Wu, Hunan, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 20/70 (2022.01); G06F 16/55 (2019.01); G06V 10/764 (2022.01); G06F 16/58 (2019.01); G06F 16/56 (2019.01); G06V 10/75 (2022.01);
U.S. Cl.
CPC ...
G06V 10/774 (2022.01); G06F 16/55 (2019.01); G06F 16/56 (2019.01); G06F 16/5866 (2019.01); G06V 10/751 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/95 (2022.01); G06V 20/70 (2022.01);
Abstract

A training method for a robust neural network based on feature matching is provided in this disclosure, which includes following steps. Step A, a first stage model is initialized. The first stage model includes a backbone network, a feature matching module and a fullple loss function. Step B, the first stage model is trained by using original training data to obtain a second stage model. Step C, the second stage model is attacked so as to generate PGD adversarial samples of the original training data, and the second stage model is trained again with the generated adversarial samples and the original training data. Step D, training parameters are adjusted and the second stage model is trained again, and parameters for which the model has highest accuracy on an original test set are saved.


Find Patent Forward Citations

Loading…