no code implementations • 28 Sep 2020 • Alexandru Țifrea, Eric Petru Stavarache, Fanny Yang
This paper studies how such ``hard'' OOD scenarios can benefit from tuning the detection method after observing a batch of the test data.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 25 Sep 2019 • Hartmut Maennel, Alexandru Țifrea
A simple method for obtaining uncertainty estimates for Neural Network classifiers (e. g. for out-of-distribution detection) is to use an ensemble of independently trained networks and average the softmax outputs.