Invention Grant
- Patent Title: Data augmentation including background modification for robust prediction using neural networks
-
Application No.: US17039437Application Date: 2020-09-30
-
Publication No.: US11688074B2Publication Date: 2023-06-27
- Inventor: Nishant Puri , Sakthivel Sivaraman , Rajath Shetty , Niranjan Avadhanam
- Applicant: NVIDIA Corporation
- Applicant Address: US CA Santa Clara
- Assignee: NVIDIA Corporation
- Current Assignee: NVIDIA Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Taylor English Duma L.L.P.
- Main IPC: G06T7/194
- IPC: G06T7/194 ; G06T5/30 ; G06T5/00 ; G06N3/08 ; G06V40/10 ; G06F18/214 ; G06F18/24

Abstract:
In various examples, a background of an object may be modified to generate a training image. A segmentation mask may be generated and used to generate an object image that includes image data representing the object. The object image may be integrated into a different background and used for data augmentation in training a neural network. Data augmentation may also be performed using hue adjustment (e.g., of the object image) and/or rendering three-dimensional capture data that corresponds to the object from selected views. Inference scores may be analyzed to select a background for an image to be included in a training dataset. Backgrounds may be selected and training images may be added to a training dataset iteratively during training (e.g., between epochs). Additionally, early or late fusion nay be employed that uses object mask data to improve inferencing performed by a neural network trained using object mask data.
Public/Granted literature
- US20220101047A1 DATA AUGMENTATION INCLUDING BACKGROUND MODIFICATION FOR ROBUST PREDICTION USING NEURAL NETWORKS Public/Granted day:2022-03-31
Information query