Energy-based Out-of-distribution Detection A Detailed Experimental Results We report the performance of OOD detectors on each of the six OOD test datasets in Table 4 (CIFAR-10) and Table 5 (CIFAR-100)

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.