Regularized multi-label classification from partially labeled training data
US10769766B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 31, 2018 |
| Grant date | Sep 8, 2020 |
| Priority date | — |
| Expiry date | Nov 22, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/30168
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Aspects of the present disclosure relate to machine learning techniques for training a model to identify each of a number of different classes in images, based on training data where each training image may not be labeled in a complete manner with respect to the classes. The disclosed training techniques use a new label value to indicate when a ground truth value is unknown for a particular class, and do not penalize the machine learning network for output predictions that do not match the label value representing unknown ground truth. Some implementations of the training process can be regularized to impose sparsity on predicted classes in order to avoid false positive predictions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.