公开(公告)号：US20240161281A1

公开(公告)日：2024-05-16

申请号：US18405922

申请日：2024-01-05

申请人： NVIDIA Corporation

发明人： Wentao Zhu ,  Daguang Xu ,  Andriy Myronenko ,  Ziyue Xu

IPC分类号： G06T7/00 ,  G06F30/20 ,  G06N3/08 ,  G06T7/11 ,  G06T7/33

CPC分类号： G06T7/0012 ,  G06F30/20 ,  G06N3/08 ,  G06T7/11 ,  G06T7/344 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.

公开(公告)号：US11804050B1

公开(公告)日：2023-10-31

申请号：US16671001

申请日：2019-10-31

申请人： NVIDIA Corporation

发明人： Fausto Milletari ,  Maximilian Baust ,  Nicola Rieke ,  Wenqi Li ,  Daguang Xu ,  Andrew Feng ,  Rong Ou ,  Yan Cheng

IPC分类号： G06V20/64 ,  G06N3/063 ,  G06N3/08 ,  G06N3/045

CPC分类号： G06V20/64 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08

摘要： Apparatuses, systems, and techniques to collaboratively train one or more machine learning models. Parameter reviewers may be configured to compare sets of machine learning model parameter information in order to generate one or more machine learning models, such as neural networks.

公开(公告)号：US20230069310A1

公开(公告)日：2023-03-02

申请号：US17398655

申请日：2021-08-10

申请人： Nvidia Corporation

发明人： Andriy Myronenko ,  Ziyue Xu ,  Dong Yang ,  Holger Roth ,  Daguang Xu

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

摘要： Apparatuses, systems, and techniques are presented to classify objects in images. In at least one embodiment, one or more neural networks are used to identify one or more objects in one or more full images based, at least in part, on the one or more neural networks having been trained using the one or more full images and one or more portions of the one or more full images.

公开(公告)号：US20230061998A1

公开(公告)日：2023-03-02

申请号：US17459644

申请日：2021-08-27

申请人： Nvidia Corporation

发明人： Dong Yang ,  Andriy Myronenko ,  Xiaosong Wang ,  Ziyue Xu ,  Holger Roth ,  Daguang Xu

IPC分类号： G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06F7/24

摘要： Apparatuses, systems, and techniques are presented to select neural networks. In at least one embodiment, one or more first neural networks can be used to select one or more second neural networks, as may be based at least in part upon an inference to be generated by the one or more second neural networks.

公开(公告)号：US20220284582A1

公开(公告)日：2022-09-08

申请号：US17190724

申请日：2021-03-03

申请人： NVIDIA Corporation

发明人： Dong Yang ,  Yufan He ,  Holger Reinhard Roth ,  Can Zhao ,  Daguang Xu

IPC分类号： G06T7/10 ,  G06T7/00 ,  G06N3/04 ,  G06N3/10

摘要： Apparatuses, systems, and techniques to select a neural network using an amount of memory to be used. In at least one embodiment, a processor includes one or more circuits to cause one or more neural networks to be selected from a plurality of neural networks based, at least in part, on an amount of memory to be used by the one oe more neural networks.

公开(公告)号：US20210397943A1

公开(公告)日：2021-12-23

申请号：US16905252

申请日：2020-06-18

申请人： NVIDIA Corporation

发明人： Pablo Ribalta ,  Michal Marcinkiewicz ,  Dong Yang ,  Daguang Xu ,  Przemyslaw Miroslaw Strzelczyk

IPC分类号： G06N3/08 ,  G06N3/04

摘要： Apparatuses, systems, and techniques to train neural networks to perform classification. In at least one embodiment, one or more neural networks are trained to perform classification based on, for example, using one or more compressed representations of one or more class labels, where the one or more compressed representations have fewer bits than a representation of the one or more class labels.

公开(公告)号：US20210374502A1

公开(公告)日：2021-12-02

申请号：US16889652

申请日：2020-06-01

申请人： NVIDIA Corporation

发明人： Holger Reinhard Roth ,  Dong Yang ,  Wenqi Li ,  Andriy Myronenko ,  Wentao Zhu ,  Ziyue Xu ,  Xiaosong Wang ,  Daguang Xu

IPC分类号： G06N3/04 ,  G06N3/08 ,  G06T7/10

摘要： Apparatuses, systems, and techniques to select a nueral network architecture from a plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a neural network is trained by combining training resutls from different FL computing systesms, where each of the different FL computing systems, for example, trains different portions of the nerual network.

公开(公告)号：US20200293828A1

公开(公告)日：2020-09-17

申请号：US16813673

申请日：2020-03-09

申请人： NVIDIA Corporation

发明人： Xiaosong Wang ,  Ziyue Xu ,  Dong Yang ,  Holger Reinhard Roth ,  Andriy Myronenko ,  Daguang Xu ,  Ling Zhang

IPC分类号： G06K9/62 ,  G06N3/063 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00

摘要： Apparatuses, systems, and techniques to perform training of neural networks using stacked transformed images. In at least one embodiment, a neural network is trained on stacked transformed images and trained neural network is provided to be used for processing images from an unseen domain distinct from a source domain, wherein stacked transformed images are transformed according to transformation aspects related to domain variations.

公开(公告)号：US20240104345A1

公开(公告)日：2024-03-28

申请号：US17859670

申请日：2022-07-07

申请人： Nvidia Corporation

发明人： Cheng Peng ,  Andriy Myronenko ,  Ali Hatamizsadeh ,  Vishwesh Nath ,  Md Mahfuzur Rahman Siddiquee ,  Yufan He ,  Daguang Xu ,  Dong Yang

IPC分类号： G06N3/04 ,  G06N3/08 ,  G16H30/20

CPC分类号： G06N3/0454 ,  G06N3/08 ,  G16H30/20

摘要： Apparatuses, systems, and techniques are presented to generate images representing realistic motion or activity. In at least one embodiment, one or more neural networks are used to select a first neural network to perform a first task based, at least in part, upon a performance estimated by a second neural network.

公开(公告)号：US11816185B1

公开(公告)日：2023-11-14

申请号：US16383347

申请日：2019-04-12

申请人： Nvidia Corporation

发明人： Holger Roth ,  Yingda Xia ,  Dong Yang ,  Daguang Xu

IPC分类号： G06F18/214 ,  G06F9/30 ,  G06N3/08 ,  G16H30/40 ,  G06N5/04 ,  G06F18/211 ,  G06F18/2433 ,  G06N3/045

CPC分类号： G06F18/2155 ,  G06F9/3001 ,  G06F18/211 ,  G06F18/2433 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04 ,  G16H30/40 ,  G06V2201/031

摘要： Volumetric quantification can be performed for various parameters of an object represented in volumetric data. Multiple views of the object can be generated, and those views provided to a set of neural networks that can generate inferences in parallel. The inferences from the different networks can be used to generate pseudo-labels for the data, for comparison purposes, which enables a co-training loss to be determined for the unlabeled data. The co-training loss can then be used to update the relevant network parameters for the overall data analysis network. If supervised data is also available then the network parameters can further be updated using the supervised loss.