公开(公告)号：US20210334975A1

公开(公告)日：2021-10-28

申请号：US16856823

申请日：2020-04-23

Applicant: Nvidia Corporation

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

IPC: G06T7/11 ,  G06T7/12 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques are presented to predict segmentations for objects in images. In at least one embodiment, a neural network is trained to determine one or more segmentation masks corresponding to one or more objects of one or more digital images based, at least in part, on one or more boundary regions of the one or more objects.

公开(公告)号：US20210012504A1

公开(公告)日：2021-01-14

申请号：US16913085

申请日：2020-06-26

Applicant: NVIDIA Corporation

Inventor： Andriy Myronenko

IPC: G06T7/11 ,  G06K9/03 ,  G06K9/62

Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.

公开(公告)号：US20240161281A1

公开(公告)日：2024-05-16

申请号：US18405922

申请日：2024-01-05

Applicant: NVIDIA Corporation

Inventor： Wentao Zhu ,  Daguang Xu ,  Andriy Myronenko ,  Ziyue Xu

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

CPC classification number: G06T7/0012 ,  G06F30/20 ,  G06N3/08 ,  G06T7/11 ,  G06T7/344 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: 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：US20230069310A1

公开(公告)日：2023-03-02

申请号：US17398655

申请日：2021-08-10

Applicant: Nvidia Corporation

Inventor： Andriy Myronenko ,  Ziyue Xu ,  Dong Yang ,  Holger Roth ,  Daguang Xu

IPC: G06T7/11 ,  G06K9/62 ,  G06N3/08

Abstract: 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

Applicant: Nvidia Corporation

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

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

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：US20210374502A1

公开(公告)日：2021-12-02

申请号：US16889652

申请日：2020-06-01

Applicant: NVIDIA Corporation

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

IPC: G06N3/04 ,  G06N3/08 ,  G06T7/10

Abstract: 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

Applicant: NVIDIA Corporation

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

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

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.