Decoupling category-wise independence and relevance with self-attention for multi-label image classification
US11494616B2 · kind B2 · utility
2Cited by
5References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 11, 2019 |
| Grant date | Nov 8, 2022 |
| Priority date | — |
| Expiry date | Aug 26, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems are provided for generating a multi-label classification system. The multi-label classification system can use a multi-label classification neural network system to identify one or more labels for an image. The multi-label classification system can explicitly take into account the relationship between classes in identifying labels. A relevance sub-network of the multi-label classification neural network system can capture relevance information between the classes. Such a relevance sub-network can decouple independence between classes to focus learning on relevance between the classes.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.