Semantic class localization in images
US9846840B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 25, 2016 |
| Grant date | Dec 19, 2017 |
| Priority date | — |
| Expiry date | May 25, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0895
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Semantic class localization techniques and systems are described. In one or more implementation, a technique is employed to back communicate relevancies of aggregations back through layers of a neural network. Through use of these relevancies, activation relevancy maps are created that describe relevancy of portions of the image to the classification of the image as corresponding to a semantic class. In this way, the semantic class is localized to portions of the image. This may be performed through communication of positive and not negative relevancies, use of contrastive attention maps to different between semantic classes and even within a same semantic class through use of a self-contrastive technique.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.