US 12,321,420 B2
Systems and methods for training generative adversarial networks and use of trained generative adversarial networks
Nhan Ngo Dinh, Rome (IT); Giulio Evangelisti, Rome (IT); and Flavio Navari, Rome (IT)
Assigned to COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED, Dublin (IE)
Filed by COSMO ARTIFICIAL INTELLIGENCE—AI LIMITED, Dublin (IE)
Filed on May 1, 2024, as Appl. No. 18/652,226.
Application 18/652,226 is a continuation of application No. 17/251,773, granted, now 12,158,924, previously published as PCT/EP2019/065256, filed on Jun. 11, 2019.
Application 17/251,773 is a continuation of application No. 16/008,006, filed on Jun. 13, 2018, granted, now 10,810,460, issued on Oct. 20, 2020.
Claims priority of application No. 18180570 (EP), filed on Jun. 28, 2018.
Prior Publication US 2024/0303299 A1, Sep. 12, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 18/2413 (2023.01); A61B 1/00 (2006.01); A61B 1/273 (2006.01); A61B 1/31 (2006.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 3/088 (2023.01); G06T 7/00 (2017.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)
CPC G06F 18/2413 (2023.01) [A61B 1/000096 (2022.02); A61B 1/273 (2013.01); A61B 1/2736 (2013.01); A61B 1/31 (2013.01); G06F 18/214 (2023.01); G06F 18/2148 (2023.01); G06F 18/217 (2023.01); G06F 18/41 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/088 (2013.01); G06T 7/0012 (2013.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10016 (2013.01); G06T 2207/10068 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30032 (2013.01); G06T 2207/30096 (2013.01); G06V 2201/032 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for training a generative adversarial network, comprising:
receiving a first plurality of feature indicators for at least one region in a first plurality of image frames, the at least one region including one or more representations of a feature-of-interest;
training a discriminator network using a first training set including the first plurality of image frames and the first plurality of feature indicators;
applying the trained discriminator network to a second plurality of image frames to produce a second plurality of feature indicators for at least one region in the second plurality of image frames, the at least one region including one or more representations of the feature-of-interest;
receiving verifications of true positives and false positives with respect to the second plurality of feature indicators; and
training a generative adversarial network using a second training set including the second plurality of image frames and the verifications.