Closed wetliu closed 4 years ago
Detection performance on datasets such as Gaussian noise vary between different model initializations. Perhaps then the results in the paper did not use this specific model, but a model a model with the same architecture. Consequently the variability you observe is predictable, and goes to show that it is important to average across many distributions. Hopefully this answers your question.
Hello. If I use your pretrained oe_tune models, the results are perfectly matched. However, I have a hard time trying to reproduce the OE fine-tune results on the paper. Some OOD datasets are off, though the average is similar. I have tried both pytorch 1.4 and 0.4. Here are the OOD datasets that are off after OE tuning (left columns are your pretrained OE model while right columns are our reproduced results). It is on cifar100_wrn_oe_tune. Would you mind taking a look and sharing your ideas/package versions? Thank you so much!