公开(公告)号：US20240095534A1

公开(公告)日：2024-03-21

申请号：US18243348

申请日：2023-09-07

Applicant: NVIDIA Corporation

Inventor： Anima Anandkumar ,  Chaowei Xiao ,  Weili Nie ,  De-An Huang ,  Zhiding Yu ,  Manli Shu

IPC: G06N3/084 ,  G06N3/045

CPC classification number: G06N3/084 ,  G06N3/045

Abstract: Apparatuses, systems, and techniques to perform neural networks. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected based, at least in part, on a plurality of variances of one or more inputs to the one or more neural networks.

公开(公告)号：US20240017745A1

公开(公告)日：2024-01-18

申请号：US17865344

申请日：2022-07-14

Applicant: NVIDIA Corporation

Inventor： Yulong Cao ,  Chaowei Xiao ,  Danfei Xu ,  Anima Anandkumar ,  Marco Pavone

IPC: B60W60/00 ,  B60W40/04 ,  B60W50/00

CPC classification number: B60W60/0027 ,  B60W40/04 ,  B60W50/0097 ,  B60W2554/4041 ,  B60W2554/4044

Abstract: Apparatuses, systems, and techniques to generate trajectory data for moving objects. In at least one embodiment, adversarial trajectories are generated to evaluate a trajectory prediction model and are based, at least in part, on a differentiable dynamic model.

公开(公告)号：US20230280726A1

公开(公告)日：2023-09-07

申请号：US17684245

申请日：2022-03-01

Applicant: NVIDIA Corporation

Inventor： Yuke Zhu ,  Anima Anandkumar ,  Youngwoon Lee

IPC: G05B19/418

CPC classification number: G05B19/41865 ,  G05B19/41885 ,  G05B19/41895

Abstract: A manipulation task may include operations performed by one or more manipulation entities on one or more objects. This manipulation task may be broken down into a plurality of sequential sub-tasks (policies). These policies may be fine-tuned so that a terminal state distribution of a given policy matches an initial state distribution of another policy that immediately follows the given policy within the plurality of policies. The fine-tuned plurality of policies may then be chained together and implemented within a manipulation environment.

公开(公告)号：US20220379484A1

公开(公告)日：2022-12-01

申请号：US17331466

申请日：2021-05-26

Applicant: NVIDIA Corporation

Inventor： Jonathan Tremblay ,  Fabio Tozeto Ramos ,  Yuke Zhu ,  Anima Anandkumar ,  Guanya Shi

IPC: B25J9/16 ,  G06T7/73 ,  G06K9/00 ,  B25J19/02 ,  B25J13/08 ,  G05B13/02 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques generate poses of an object based on data of the object observed from a first viewpoint and a second viewpoint. The poses can be evaluated to determine a portion of the data usable by an estimator to generate a pose of the object.

公开(公告)号：US11941899B2

公开(公告)日：2024-03-26

申请号：US17331451

申请日：2021-05-26

Applicant: NVIDIA Corporation

Inventor： Jonathan Tremblay ,  Fabio Tozeto Ramos ,  Yuke Zhu ,  Anima Anandkumar ,  Guanya Shi

IPC: B25J9/16 ,  B25J13/08 ,  B25J19/02 ,  G05B13/02 ,  G06F18/214 ,  G06K9/00 ,  G06N3/04 ,  G06N3/045 ,  G06T7/73 ,  G06V10/75 ,  G06V20/64

CPC classification number: G06V20/653 ,  G06F18/2148 ,  G06N3/045 ,  G06V10/751

Abstract: Apparatuses, systems, and techniques generate poses of an object based on image data of the object obtained from a first viewpoint of the object and a second viewpoint of the object. The poses can be evaluated to determine a portion of the image data usable by an estimator to generate a pose of the object.

公开(公告)号：US20240095447A1

公开(公告)日：2024-03-21

申请号：US17846866

申请日：2022-06-22

Applicant: Nvidia Corporation

Inventor： Wei Ping ,  Boxin Wang ,  Chaowei Xiao ,  Mohammad Shoeybi ,  Mostofa Patwary ,  Anima Anandkumar ,  Bryan Catanzaro

IPC: G06F40/279 ,  G06F40/205 ,  G06F40/55

CPC classification number: G06F40/279 ,  G06F40/205 ,  G06F40/55

Abstract: Apparatuses, systems, and techniques are presented to identify and prevent generation of restricted content. In at least one embodiment, one or more neural networks are used to identify restricted content based only on the restricted content.

公开(公告)号：US20240062534A1

公开(公告)日：2024-02-22

申请号：US17893038

申请日：2022-08-22

Applicant: NVIDIA Corporation

Inventor： Xiaojian Ma ,  Weili Nie ,  Zhiding Yu ,  Huaizu Jiang ,  Chaowei Xiao ,  Yuke Zhu ,  Anima Anandkumar

IPC: G06V10/82 ,  G06V10/20 ,  G06V10/94

CPC classification number: G06V10/82 ,  G06V10/255 ,  G06V10/94

Abstract: A vision transformer (ViT) is a deep learning model that performs one or more vision processing tasks. ViTs may be modified to include a global task that clusters images with the same concept together to produce semantically consistent relational representations, as well as a local task that guides the ViT to discover object-centric semantic correspondence across images. A database of concepts and associated features may be created and used to train the global and local tasks, which may then enable the ViT to perform visual relational reasoning faster, without supervision, and outside of a synthetic domain.

公开(公告)号：US20230015989A1

公开(公告)日：2023-01-19

申请号：US17365877

申请日：2021-07-01

Applicant: Nvidia Corporation

Inventor： Zhiding Yu ,  Rui Huang ,  Wonmin Byeon ,  Sifei Liu ,  Guilin Liu ,  Thomas Breuel ,  Anima Anandkumar ,  Jan Kautz

IPC: G06K9/46 ,  G06N3/04 ,  G06T7/13 ,  G06K9/62

Abstract: The disclosure provides a learning framework that unifies both semantic segmentation and semantic edge detection. A learnable recurrent message passing layer is disclosed where semantic edges are considered as explicitly learned gating signals to refine segmentation and improve dense prediction quality by finding compact structures for message paths. The disclosure includes a method for coupled segmentation and edge learning. In one example, the method includes: (1) receiving an input image, (2) generating, from the input image, a semantic feature map, an affinity map, and a semantic edge map from a single backbone network of a convolutional neural network (CNN), and (3) producing a refined semantic feature map by smoothing pixels of the semantic feature map using spatial propagation, and controlling the smoothing using both affinity values from the affinity map and edge values from the semantic edge map.

公开(公告)号：US20210334644A1

公开(公告)日：2021-10-28

申请号：US16859360

申请日：2020-04-27

Applicant: NVIDIA Corporation

Inventor： Zhiding Yu ,  Wuyang Chen ,  Anima Anandkumar

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to train one or more neural networks. In at least one embodiment, one or more neural networks are trained based, at least in part, on inferencing output from one or more second neural networks.

公开(公告)号：US20250020481A1

公开(公告)日：2025-01-16

申请号：US18681836

申请日：2022-04-07

Applicant: NVIDIA Corporation

Inventor： Enze Xie ,  Zhiding Yu ,  Jonah Philion ,  Anima Anandkumar ,  Sanja Fidler ,  Jose Manuel Alvarez Lopez

IPC: G01C21/00 ,  G06T7/11 ,  G06T7/73 ,  G06T17/05

Abstract: Apparatuses, systems, and techniques are presented to determination about objects in an environment. In at least one embodiment, a neural network can be used to determine one or more positions of one or more objects within a three-dimensional (3D) environment and to generate a segmented map of the 3D environment based, at least in part, on one or more two dimensional (2D) images of the one or more objects.