Calibrating Deep Neural Networks using Focal Loss — mentioned by Isinlor

Sun, 27 Dec 2020 01:01:55 GMT

It's an active research field. E.g. from October 2020: Calibrating Deep Neural Networks using Focal Loss: https://arxiv.org/abs/2002.09437 > 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 [Lin et. al., 2017] allows us to learn models that are already very well calibrated. When combined with temperature scaling, whilst preserving accuracy, it yields…

Paper and discussion history. A mention is not an endorsement.

Calibrating Deep Neural Networks using Focal Loss · HackerPapers discussions

Calibrating Deep Neural Networks using Focal Loss — mentioned by Isinlor