Joint training of neural networks using multi scale hard example mining
US11120314B2 · kind B2 · utility
1Cited by
0References
25Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Apr 7, 2017 |
| Grant date | Sep 14, 2021 |
| Priority date | — |
| Expiry date | Oct 13, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/2504
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.