Training end-to-end video processes

Z Wang, RD Bishop, F Huszar, L Theis - US Patent 10,681,361, 2020 - Google Patents
Methods and systems for optimising the quality of visual data. Specifically, methods and
systems for preserving visual information during compression and decompression. An …

Generative adversarial network medical image generation for training of a classifier

A Madani, M Moradi, TF Syeda-Mahmood - US Patent 10,592,779, 2020 - Google Patents
Mechanisms are provided to implement a machine learning training model. The machine
learning training model trains an image generator of a generative adversarial network (GAN) …

Machine learning for visual processing

Z Wang, RD Bishop, W Shi, J Caballero… - US Patent …, 2022 - Google Patents
(57) ABSTRACT A method for develo** an enhancement model for low quality visual data,
the method comprising the steps of receiving one or more sections of higher-quality visual …

Automatic liver segmentation using adversarial image-to-image network

D Yang, D Xu, SK Zhou, B Georgescu, M Chen… - US Patent …, 2020 - Google Patents
(Continued) Primary Examiner—Tahmina N Ansari (57) ABSTRACT A method and
apparatus for automated liver segmentation in a 3D medical image of a patient is disclosed …

Capsule GAN for prostate MRI super-resolution

M Molahasani Majdabadi, Y Choi… - Multimedia Tools and …, 2022 - Springer
Prostate cancer is a prevalent disease among adult men. One in seven Canadian men is
diagnosed with this cancer in their lifetime. Super-Resolution (SR) can facilitate early …

Adapting a generative adversarial network to new data sources for image classification

A Madani, M Moradi, TF Syeda-Mahmood - US Patent 10,540,578, 2020 - Google Patents
Mechanisms are provided to implement a generative adver sarial network (GAN) that is
trained based on labeled image data, unlabeled image data, and generated image data gen …

Automatic image correction using machine learning

CC Ferrer, B Dolhansky, TW Meyer… - US Patent 10,388,002, 2019 - Google Patents
In one embodiment, a computing system may access a training image and a reference
image of a person and an incomplete image. A generate may generate an in-painted image …

Adversarial and dual inverse deep learning networks for medical image analysis

SK Zhou, M Chen, D Xu, XU Zhoubing… - US Patent …, 2020 - Google Patents
Methods and apparatus for automated medical image analysis using deep learning
networks are disclosed. In a method of automatically performing a medical image analysis …

Adapting simulation data to real-world conditions encountered by physical processes

H Li, EP Atherton, E Bradner, N Cote… - US Patent …, 2022 - Google Patents
One embodiment of the present invention sets forth a technique for generating simulated
training data for a physi cal process. The technique includes receiving, as input to at least …

Medical image classification based on a generative adversarial network trained discriminator

A Madani, M Moradi, TF Syeda-Mahmood - US Patent 10,937,540, 2021 - Google Patents
Mechanisms are provided to implement a generative adver sarial network (GAN). A
discriminator of the GAN is configured to discriminate input medical images into a plurality of …