IP Library Granted Patent US 11,797,864
Granted Patent B2
US 11,797,864 · App. 16/194,211 · Granted Oct 24, 2023

Systems and methods for conditional generative models

Inventors: Shabab Bazrafkan (Galway, IE); Peter Corcoran (Galway, IE)
G06N3/094G06N3/045G06N3/08G06N3/084G06N3/088G06N7/00G06N20/00G06V10/764G06V10/774G06V10/82G06V40/168G06F18/214G06F18/2431
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,797,864
App. No.
16/194,211
Granted
Oct 24, 2023
Kind
B2
Abstract

Systems and methods for training a conditional generator model are described. Methods receive a sample, and determine a discriminator loss for the received sample. The discriminator loss is based on an ability to determine whether the sample is generated by the conditional generator model or is a ground truth sample. The method determines a secondary loss for the generated sample and updates the conditional generator model based on an aggregate of the discriminator loss and the secondary loss.

Claims (32)

1. A method for training a conditional generator model, the method comprising:

receiving a sample;

determining a discriminator loss for the received sample, wherein the discriminator loss is based on an ability to determine whether the sample is generated by the conditional generator model or is a ground truth sample;

determining a plurality of secondary losses for the generated sample using a binary classification model, a multi-class classification model and a regression model, wherein the binary classification model, the multi-class classification model and the regression model are within the conditional generator model;

updating the conditional generator model based on an aggregate of the discriminator loss and the plurality of secondary losses; and

generating images with one or more landmarks, wherein the generated images have higher diversity than the received sample.

2. The method of claim 1 , wherein the steps of receiving, determining a discriminator loss, determining a plurality of secondary losses, and updating the conditional generator model are performed iteratively.

3. The method of claim 2 , wherein determining the secondary loss for a first iteration is performed using a first secondary loss model and determining the secondary loss for a second iteration is performed using a different second secondary loss model.

4. The method of claim 1 , wherein the sample comprises an associated label and wherein the multi-class classification model is trained to classify the sample into one of a plurality of classes.

5. The method of claim 4 , wherein the classification model is a pre-trained model that is not modified during the training of the conditional generator model.

6. The method of claim 1 , wherein the regression model is trained to predict a continuous aspect of the sample.

7. The method of claim 1 , wherein the aggregate is a weighted average of the discriminator loss and the plurality of secondary losses.

8. The method of claim 7 , wherein the steps of receiving, determining a discriminator loss, determining a plurality of secondary losses, and updating the conditional generator model are performed iteratively, wherein a weight used for calculating the weighted average is different between different iterations.

9. The method of claim 1 further comprising:

generating a set of outputs using the trained conditional generator model, wherein the set of outputs comprises a set of samples and a set of associated output labels; and

training a new model using the set of generated outputs that does not include any samples.

10. A system comprising memory and one or more processors configured to:

receive a sample;

determine a discriminator loss for the received sample, wherein the discriminator loss is based on an ability to determine whether the sample is generated by a conditional generator model or is a ground truth sample;

determine a plurality of secondary losses for the sample using a binary classification model, a multi-class classification model and a regression model, wherein the binary classification model, the multi-class classification model and the regression model are within the conditional generator model;

update the conditional generator model based on an aggregate of the discriminator loss and the plurality of secondary losses; and

generating images with one or more landmarks, wherein the generated images have higher diversity than the received sample.

11. The system of claim 10 , wherein the receiving, determining a discriminator loss, determining a plurality of secondary losses, and updating the conditional generator model are performed iteratively.

12. The system of claim 11 , wherein the one or more processors are configured to determine the secondary loss for a first iteration using a first secondary loss model and determining the secondary loss for a second iteration is performed using a different second secondary loss model.

13. The system claim 10 , wherein the sample comprises an associated label and wherein the multi-class classification model is trained to classify the sample into one of a plurality of classes.

14. The system of claim 13 , wherein the classification model is a pre-trained model that is not modified during the training of the conditional generator model.

15. The system of claim 10 , wherein the regression model is trained to predict a continuous aspect of the sample.

16. The system of claim 10 , wherein the aggregate is a weighted average of the discriminator loss and the secondary loss.

17. The system of claim 16 , wherein the receiving, determining a discriminator loss, determining a secondary loss, and updating the conditional generator model are performed iteratively, wherein a weight used for calculating the weighted average is different between different iterations.

18. The system of claim 10 , wherein the one or more processors are further configured to:

generate a set of outputs using the trained conditional generator model, wherein the set of outputs comprises a set of samples and a set of associated output labels; and

train a new model using the set of generated outputs that does not include any samples.

Assignments (6)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 12, 2025
From: TOBII TECHNOLOGIES LTD
To: ADEIA MEDIA HOLDINGS LLC
Reel/Frame 071572/0855 →
CONVERSION Recorded Jun 12, 2025
From: ADEIA MEDIA HOLDINGS LLC
To: ADEIA MEDIA HOLDINGS INC.
Reel/Frame 071577/0875 →
SECURITY INTEREST Recorded May 28, 2025
From: ADEIA INC. (F/K/A XPERI HOLDING CORPORATION); ADEIA HOLDINGS INC.; ADEIA MEDIA HOLDINGS INC.; ADEIA IMAGING LLC; ADEIA MEDIA LLC; ADEIA MEDIA SOLUTIONS INC.; ADEIA SEMICONDUCTOR BONDING TECHNOLOGIES INC.; ADEIA TECHNOLOGIES INC.; ADEIA GUIDES INC.; ADEIA SOLUTIONS LLC; ADEIA SEMICONDUCTOR ADVANCED TECHNOLOGIES INC.; ADEIA SEMICONDUCTOR SOLUTIONS LLC; ADEIA SEMICONDUCTOR INTELLECTUAL PROPERTY LLC; ADEIA SEMICONDUCTOR TECHNOLOGIES LLC; ADEIA PUBLISHING INC.
To: BANK OF AMERICA, N.A., AS COLLATERAL AGENT
Reel/Frame 071454/0343 →
CHANGE OF NAME Recorded Dec 5, 2024
From: FOTONATION LIMITED
To: TOBII TECHNOLOGIES LIMITED
Reel/Frame 069516/0394 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 30, 2019
From: NATIONAL UNIVERSITY OF IRELAND, GALWAY
To: FOTONATION LIMITED
Reel/Frame 049908/0807 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 30, 2018
From: CORCORAN, PETER; BAZRAFKAN, SHABAB
To: FOTONATION LIMITED; NATIONAL UNIVERSITY OF IRELAND, GALWAY
Reel/Frame 047646/0430 →
Continuity (2)
Provisional Application 62686472 · Jun 18, 2018
Related Publication 20190385019A1 · Dec 19, 2019