Zero-Shot Out-of-Distribution Detection with Feature Correlations
Anonymized Code for openreview submission: https://openreview.net/forum?id=r1g6MCEtwr
Dependencies
The code is written in Python 2 with Pytorch 1.0.
Results
Downloading Pre-trained Models
We used pre-trained neural networks open-sourced by Mahalanobis and odin-pytorch. The DenseNets trained on CIFAR-10 and CIFAR-100 are by ODIN; remaining are by Mahalanobis:
- DenseNet on CIFAR-10 / DenseNet on CIFAR-100 / DenseNet on SVHN
- ResNet on CIFAR-10 / ResNet on CIFAR-100 / ResNet on SVHN
Downloading Out-of-Distribtion Datasets
We use download links of three out-of-distribution datasets from odin-pytorch: