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. 25, 2024

Filed:

Nov. 13, 2020
Applicant:

Five Ai Limited, Bristol, GB;

Inventors:

Luca Bertinetto, Oxford, GB;

Romain Mueller, Cambridge, GB;

Konstantinos Tertikas, Oxford, GB;

Sina Samangooei, Cambridge, GB;

Nicholas A Lord, Oxford, GB;

Assignee:

Five AI Limited, Cambridge, GB;

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06F 18/243 (2023.01); G06F 17/18 (2006.01); G06F 18/2411 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06F 18/24323 (2023.01); G06F 17/18 (2013.01); G06F 18/2411 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01);
Abstract

A perception model is trained to classify inputs in relation to a discrete set of leaf node classes. A hierarchical classification tree encodes hierarchical relationships between the leaf node classes. A training loss function is dependent on a classification score for a given training input a its ground truth leaf node class of the training input, but also classification scores for at least some others of the leaf node classes, with the classification scores of the other leaf node classes weighted in dependence on their hierarchical relationship to the ground truth leaf node class within the hierarchical classification tree.


Find Patent Forward Citations

Loading…