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:
Dec. 21, 2021

Filed:

Jul. 13, 2021
Applicant:

Institute of Automation, Chinese Academy of Sciences, Beijing, CN;

Inventors:

Zhengxing Wu, Beijing, CN;

Junzhi Yu, Beijing, CN;

Yue Lu, Beijing, CN;

Xingyu Chen, Beijing, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06K 9/62 (2006.01); G06T 7/70 (2017.01); G06T 7/60 (2017.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06K 9/46 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6257 (2013.01); G06K 9/46 (2013.01); G06K 9/6262 (2013.01); G06K 9/6268 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06T 7/60 (2013.01); G06T 7/70 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

A single-stage small-sample-object detection method based on decoupled metric is provided to solve the following problems: low detection accuracy of existing small-sample-object detection methods, the mutual interference between classification and regression in a non-decoupled form, and over-fitting during training of a detection network in case of small samples. The method includes: obtaining a to-be-detected image as an input image; and obtaining a class and a regression box corresponding to each to-be-detected object in the input image through a pre-constructed small-sample-object detection network DMNet, where the DMNet includes a multi-scale feature extraction network, a decoupled representation transformation module, an image-level distance metric learning module and a regression box prediction module. The new method avoids the over-fitting during training of the detection network, eliminates the mutual interference between the classification branch and the regression branch, and improves the accuracy of small-sample-object detection.


Find Patent Forward Citations

Loading…