Complexity-based progressive training for machine vision models
US11062180B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 18, 2018 |
| Grant date | Jul 13, 2021 |
| Priority date | — |
| Expiry date | Jul 18, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/2411
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems for training machine vision models (MVMs) with “noisy” training datasets are described. A noisy set of images is received, where labels for some of the images are “noisy” and/or incorrect. A progressively-sequenced learning curriculum is designed for the noisy dataset, where the images that are easiest to learn machine-vision knowledge from are sequenced near the beginning of the curriculum and images that are harder to learn machine-vision knowledge from are sequenced later in the curriculum. An MVM is trained via providing the sequenced curriculum to a supervised learning method, so that the MVM learns from the easiest examples first and the harder training examples later, i.e., the MVM progressively accumulates knowledge from simplest to most complex. To sequence the curriculum, the training images are embedded in a feature space and the “complexity” of each image is determined via density distributions and clusters in the feature space.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.