I have seen enough: Transferring parts across categories
The recent successes of deep learning have been possible due to the availability of increasingly large quantities of annotated data. A natural question, therefore, is whether further progress can be indefinitely sustained by annotating more data, or whether there is a saturation point beyond which a...
| Main Authors: | , , |
|---|---|
| 格式: | Conference item |
| 出版: |
British Machine Vision Association and Society for Pattern Recognition
2016
|