公开(公告)号：US20240296205A1

公开(公告)日：2024-09-05

申请号：US18656298

申请日：2024-05-06

申请人： Nvidia Corporation

发明人： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

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

CPC分类号： G06F18/2148 ,  G06F18/217 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

摘要： 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：US20220108134A1

公开(公告)日：2022-04-07

申请号：US17226534

申请日：2021-04-09

申请人： Nvidia Corporation

发明人： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

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

摘要： 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：US11989262B2

公开(公告)日：2024-05-21

申请号：US17226534

申请日：2021-04-09

申请人： Nvidia Corporation

发明人： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

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

CPC分类号： G06F18/2148 ,  G06F18/217 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

摘要： 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：US20220067983A1

公开(公告)日：2022-03-03

申请号：US17006702

申请日：2020-08-28

申请人： NVIDIA Corporation

发明人： Sanja Fidler ,  David Acuna Marrero ,  Seung Wook Kim ,  Karsten Julian Kreis ,  Huan Ling

IPC分类号： G06T9/00 ,  G06N3/08 ,  G06K9/62 ,  G06T7/11

摘要： Apparatuses, systems, and techniques to generate complete depictions of objects based on a partial depiction of the object. In at least one embodiment, an image of a complete object is generated by one or more neural networks, based on an image of a portion of the object, using an encoder of the one or more neural networks trained using training data generated from output of a decoder of the one or more neural networks.