Object detection in images
US10755099B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 13, 2018 |
| Grant date | Aug 25, 2020 |
| Priority date | — |
| Expiry date | Feb 5, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.