Systems and methods for open vocabulary object detection
US12198453B2 · kind B2 · utility
0Cited by
5References
17Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 28, 2022 |
| Grant date | Jan 14, 2025 |
| Priority date | — |
| Expiry date | Jan 22, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19173
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments described herein provide methods and systems for open vocabulary object detection of images. given a pre-trained vision-language model and an image-caption pair, an activation map may be computed in the image that corresponds to an object of interest mentioned in the caption. The activation map is then converted into a pseudo bounding-box label for the corresponding object category. The open vocabulary detector is then directly supervised by these pseudo box-labels, which enables training object detectors with no human-provided bounding-box annotations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.