公开(公告)号：WO2020190561A1

公开(公告)日：2020-09-24

申请号：PCT/US2020/021777

申请日：2020-03-09

Applicant: NVIDIA CORPORATION

Inventor： XU, Daguang ,  ROTH, Holger Reinhard ,  XU, Ziyue ,  WANG, Xiaosong ,  YANG, Dong ,  MYRONENKO, Andriy ,  ZHANG, Ling

IPC: G06T7/11 ,  G06K9/00 ,  G06N3/08

Abstract: 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：WO2022026428A1

公开(公告)日：2022-02-03

申请号：PCT/US2021/043251

申请日：2021-07-26

Applicant: NVIDIA CORPORATION

Inventor： XU, Ziyue ,  WANG, Xiaosong ,  YANG, Dong ,  ROTH, Holger, Reinhard ,  ZHAO, Can ,  ZHU, Wentao ,  XU, Daguang

IPC: G06N3/08 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to train one or more neural networks to generate labels for unsupervised or partially-supervised data. In at least one embodiment, one or more pseudolabels are generated by a training framework based on available weak annotations for an input medical image, and combined with feature information about said input medical image generated by one or more neural networks to generate a label about said input medical image.

公开(公告)号：WO2023028109A1

公开(公告)日：2023-03-02

申请号：PCT/US2022/041321

申请日：2022-08-24

Applicant: NVIDIA CORPORATION

Inventor： XU, Daguang ,  WANG, Xiaosong ,  TAM, Lickkong ,  BHALODIA, Riddhish ,  LU, Kevin ,  WEN, Yuhong ,  HATMIZADEH, Ali

IPC: G06V10/82 ,  G06V10/94 ,  G06V20/62 ,  G06V30/413 ,  G06V20/70

Abstract: Apparatuses, systems, and techniques are presented to detect one or more objects in one or more images. In at least one embodiment, one or more neural networks can be used to detect one or more objects in one or more images based, at least in part, on textual descriptions of the one or more objects.

公开(公告)号：WO2023028111A1

公开(公告)日：2023-03-02

申请号：PCT/US2022/041324

申请日：2022-08-24

Applicant: NVIDIA CORPORATION

Inventor： YANG, Dong ,  MYRONENKO, Andriy ,  WANG, Xiaosong ,  XU, Ziyue ,  ROTH, Holger ,  XU, Daguang

IPC: G06N3/04 ,  G06N3/08 ,  G06T7/00 ,  G06T7/11

Abstract: 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：WO2023287911A1

公开(公告)日：2023-01-19

申请号：PCT/US2022/037005

申请日：2022-07-13

Applicant: NVIDIA CORPORATION

Inventor： XU, Ziyue ,  MYRONENKO, Andriy ,  YANG, Dong ,  ROTH, Holger, Reinhard ,  ZHAO, Can ,  WANG, Xiaosong ,  XU, Daguang

IPC: G06V10/44 ,  G06V10/82

Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, boundaries of an object within an image can be identified based, at least in part, on a user-generated outline of only a portion of this object or information about a size of this object provided by a user.

公开(公告)号：WO2022187167A1

公开(公告)日：2022-09-09

申请号：PCT/US2022/018217

申请日：2022-02-28

Applicant: NVIDIA CORPORATION

Inventor： HATAMIZADEH, Ali ,  XU, Daguang ,  WANG, Xiaosong ,  TAM, Lickkong ,  BHALODIA, Riddhish

IPC: G06N3/08 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to train a neural network to infer a condition based on an image. In at least one embodiment, a first portion of a neural network is trained to infer a condition from an image using a first dataset, and a second portion of the neural network is trained using a second dataset.

公开(公告)号：WO2021247338A1

公开(公告)日：2021-12-09

申请号：PCT/US2021/034367

申请日：2021-05-26

Applicant: NVIDIA CORPORATION

Inventor： ROTH, Holger Reinhard ,  YANG, Dong ,  LI, Wenqi ,  MYRONENKO, Andriy ,  ZHU, Wentao ,  XU, Ziyue ,  WANG, Xiaosong ,  XU, Daguang

IPC: G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06N3/0454 ,  G06N3/084 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T7/10 ,  G06V10/95 ,  G06V10/955 ,  G06V20/56 ,  G06V20/695

Abstract: Apparatuses, systems, and techniques to select a neural network architecture from a plurality of neural networks in a federated learning (FL) setting. In at least one embodiment, a neural network is trained by combining training results from different FL computing systems where each of the different FL computing systems, for example, trains different portions of the neural network.

公开(公告)号：WO2021247330A1

公开(公告)日：2021-12-09

申请号：PCT/US2021/034317

申请日：2021-05-26

Applicant: NVIDIA CORPORATION

Inventor： WANG, Xiaosong ,  XU, Ziyue ,  YANG, Dong ,  TAM, Lickkong ,  XU, Daguang

IPC: G06N3/04 ,  G06N3/08 ,  G06F40/20 ,  G06K9/6256 ,  G06K9/6267 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/084

Abstract: Apparatuses, systems, and techniques to select labels of training images to train a network. In at least one embodiment, one or more labels of training images are selected to train a network.