Calibrating deep neural networks using focal loss
Miscalibration -- a mismatch between a model's confidence and its correctness -- of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as opposed to the standard cross-entropy loss, focal loss (L...
| Main Authors: | , , , , , |
|---|---|
| Formato: | Conference item |
| Idioma: | English |
| Publicado em: |
Curran Associates
2020
|