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:
Oct. 17, 2023

Filed:

May. 16, 2023
Applicant:

Wuhan University, Hubei, CN;

Inventors:

Bo Du, Hubei, CN;

Juhua Liu, Hubei, CN;

Qihuang Zhong, Hubei, CN;

Lifang'an Xiao, Hubei, CN;

Assignee:

WUHAN UNIVERSITY, Hubei, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 7/00 (2017.01); G06T 7/174 (2017.01); G06V 10/82 (2022.01); G06V 10/774 (2022.01); G06V 10/764 (2022.01); G06T 1/20 (2006.01); G06T 7/11 (2017.01);
U.S. Cl.
CPC ...
G06T 7/174 (2017.01); G06T 1/20 (2013.01); G06T 7/11 (2017.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06T 2207/20004 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

The invention discloses an attention-based joint image and feature adaptive semantic segmentation method. First, the image adaptation procedure is used to transform the source domain image Xto a target-domain-like image Xwith an appearance similar with the target domain image X, to reduce the domain gap between the source domain and the target domain at the image appearance level; then using the feature adaptation procedure to align the features between Xand Xin the semantic prediction space and the image generation space, respectively, to extract the domain-invariant features, to reduce the domain difference between Xand X. In addition, the present invention introduces an attention module in the feature adaptation procedure to help the feature adaptation procedure pay more attention to image regions worthy of attention. Finally, combining the image adaptation procedure and the feature adaptation procedure in the end-to-end manner. The present invention effectively solves the problem of domain gap existing in the cross-modal image semantic segmentation, improves the performance of the semantic segmentation model, and achieves the optimal effect in multiple public data sets.


Find Patent Forward Citations

Loading…