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.
Patent No.:
Date of Patent:
Jan. 07, 2025
Filed:
Feb. 03, 2022
Applicant:
Carnegie Mellon University, Pittsburgh, PA (US);
Inventors:
Ran Tao, Pittsburgh, PA (US);
Marios Savvides, Pittsburgh, PA (US);
Assignee:
Carnegie Mellon University, Pittsburgh, PA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2022.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/771 (2022.01);
U.S. Cl.
CPC ...
G06V 10/7715 (2022.01); G06V 10/764 (2022.01); G06V 10/771 (2022.01);
Abstract
Disclosed herein is a methodology for refining novel-class features in a few-shot learning scenario by fine-tuning the feature extractor by reducing both class-agnostic biases and class-specific biases. A distribution calibration module is used to reduce the class-agnostic bias by normalizing the overall feature distribution for novel classes and further reshaping the feature manifold for fast adaptation during fine-tuning. Selected sampling is used to reduce class-specific bias by augmenting more data for better estimation.