公开(公告)号：US11899749B2

公开(公告)日：2024-02-13

申请号：US17201816

申请日：2021-03-15

Applicant: NVIDIA Corporation

Inventor： Subhashree Radhakrishnan ,  Partha Sriram ,  Farzin Aghdasi ,  Seunghwan Cha ,  Zhiding Yu

IPC: G06F18/214 ,  G06T7/12 ,  G06T3/00 ,  G06V10/22 ,  G06V10/24 ,  G06V20/40

CPC classification number: G06F18/214 ,  G06T3/0006 ,  G06T7/12 ,  G06V10/22 ,  G06V10/242 ,  G06V20/40 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: In various examples, training methods as described to generate a trained neural network that is robust to various environmental features. In an embodiment, training includes modifying images of a dataset and generating boundary boxes and/or other segmentation information for the modified images which is used to train a neural network.

公开(公告)号：US20220292306A1

公开(公告)日：2022-09-15

申请号：US17201816

申请日：2021-03-15

Applicant: NVIDIA Corporation

Inventor： Subhashree Radhakrishnan ,  Partha Sriram ,  Farzin Aghdasi ,  Seunghwan Cha ,  Zhiding Yu

IPC: G06K9/62 ,  G06K9/20 ,  G06K9/32 ,  G06T3/00 ,  G06T7/12 ,  G06K9/00

Abstract: In various examples, training methods as described to generate a trained neural network that is robust to various environmental features. In an embodiment, training includes modifying images of a dataset and generating boundary boxes and/or other segmentation information for the modified images which is used to train a neural network.