Data augmentation including background modification for robust prediction using neural networks
US11688074B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 30, 2020 |
| Grant date | Jun 27, 2023 |
| Priority date | — |
| Expiry date | Jun 24, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30196
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.