The Maha-lanobis score is calculated using the features of the second-to-last layer. Bold numbers are superior results. We fine-tune the models once with a fixed random seed. OE [15], reported performance for each OOD dataset is averaged over 10 random batches of samples. The Maha-lanobis scores are calculated from the features of the second-to-last layer.

The Maha-lanobis score is calculated using the features of the second-to-last layer. Bold numbers are superior results. We fine-tune the models once with a fixed random seed. OE [15], reported performance for each OOD dataset is averaged over 10 random batches of samples. The Maha-lanobis scores are calculated from the features of the second-to-last layer.

Determining whether inputs are out-of-distribution (OOD) is an essential building block for safely deploying machine learning models in the open world. However, previous methods relying on the softmax confidence score suffer from overconfident posterior distributions for OOD data. We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach using the softmax scores. Unlike softmax confidence scores, energy scores are theoretically aligned with the probability density of the inputs and are less susceptible to the overconfidence issue. Within this framework, energy can be flexibly used as a scoring function for any pre-trained neural classifier as well as a trainable cost function to shape the energy surface explicitly for OOD detection. On a CIFAR-10 pre-trained WideResNet, using the energy score reduces the average FPR (at TPR 95%) by 18.03% compared to the softmax confidence score. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.