公开(公告)号：US11989262B2

公开(公告)日：2024-05-21

申请号：US17226534

申请日：2021-04-09

Applicant: Nvidia Corporation

Inventor： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

IPC: G06F18/214 ,  G06F18/21 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

CPC classification number: G06F18/2148 ,  G06F18/217 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

Abstract: Approaches presented herein provide for unsupervised domain transfer learning. In particular, three neural networks can be trained together using at least labeled data from a first domain and unlabeled data from a second domain. Features of the data are extracted using a feature extraction network. A first classifier network uses these features to classify the data, while a second classifier network uses these features to determine the relevant domain. A combined loss function is used to optimize the networks, with a goal of the feature extraction network extracting features that the first classifier network is able to use to accurately classify the data, but prevent the second classifier from determining the domain for the image. Such optimization enables object classification to be performed with high accuracy for either domain, even though there may have been little to no labeled training data for the second domain.

公开(公告)号：US20220383073A1

公开(公告)日：2022-12-01

申请号：US17827141

申请日：2022-05-27

Applicant: NVIDIA Corporation

Inventor： David Jesus Acuna Marrero ,  Sanja Fidler ,  Marc Law ,  Guojun Zhang

IPC: G06N3/04 ,  G06N3/08

Abstract: In various examples, machine learning models (MLMs) may be updated using multi-order gradients in order to train the MLMs, such as at least a first order gradient and any number of higher-order gradients. At least a first of the MLMs may be trained to generate a representation of features that is invariant to a first domain corresponding to a first dataset and a second domain corresponding to a second dataset. At least a second of the MLMs may be trained to classify whether the representation corresponds to the first domain or the second domain. At least a third of the MLMs may trained to perform a task. The first dataset may correspond to a labeled source domain and the second dataset may correspond to an unlabeled target domain. The training may include transferring knowledge from the first domain to the second domain in a representation space.

公开(公告)号：US20220108134A1

公开(公告)日：2022-04-07

申请号：US17226534

申请日：2021-04-09

Applicant: Nvidia Corporation

Inventor： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06K9/46

Abstract: Approaches presented herein provide for unsupervised domain transfer learning. In particular, three neural networks can be trained together using at least labeled data from a first domain and unlabeled data from a second domain. Features of the data are extracted using a feature extraction network. A first classifier network uses these features to classify the data, while a second classifier network uses these features to determine the relevant domain. A combined loss function is used to optimize the networks, with a goal of the feature extraction network extracting features that the first classifier network is able to use to accurately classify the data, but prevent the second classifier from determining the domain for the image. Such optimization enables object classification to be performed with high accuracy for either domain, even though there may have been little to no labeled training data for the second domain.

公开(公告)号：US20240296205A1

公开(公告)日：2024-09-05

申请号：US18656298

申请日：2024-05-06

Applicant: Nvidia Corporation

Inventor： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

IPC: G06F18/214 ,  G06F18/21 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

CPC classification number: G06F18/2148 ,  G06F18/217 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

Abstract: Approaches presented herein provide for unsupervised domain transfer learning. In particular, three neural networks can be trained together using at least labeled data from a first domain and unlabeled data from a second domain. Features of the data are extracted using a feature extraction network. A first classifier network uses these features to classify the data, while a second classifier network uses these features to determine the relevant domain. A combined loss function is used to optimize the networks, with a goal of the feature extraction network extracting features that the first classifier network is able to use to accurately classify the data, but prevent the second classifier from determining the domain for the image. Such optimization enables object classification to be performed with high accuracy for either domain, even though there may have been little to no labeled training data for the second domain.