Multi-layer fusion in a convolutional neural network for image classification
US10068171B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 10, 2016 |
| Grant date | Sep 4, 2018 |
| Priority date | — |
| Expiry date | Jul 12, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V2201/08
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and system for domain adaptation based on multi-layer fusion in a convolutional neural network architecture for feature extraction and a two-step training and fine-tuning scheme. The architecture concatenates features extracted at different depths of the network to form a fully connected layer before the classification step. First, the network is trained with a large set of images from a source domain as a feature extractor. Second, for each new domain (including the source domain), the classification step is fine-tuned with images collected from the corresponding site. The features from different depths are concatenated with and fine-tuned with weights adjusted for a specific task. The architecture is used for classifying high occupancy vehicle images.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.