Original Pdf: pdf
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CIFAR-100](https://paperswithcode.com/dataset/cifar-100), [CelebA](https://paperswithcode.com/dataset/celeba), [ImageNet](https://paperswithcode.com/dataset/imagenet), [LSUN](https://paperswithcode.com/dataset/lsun), [SVHN](https://paperswithcode.com/dataset/svhn)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1911.11943/code)
Keywords: novelty, anomaly, uncertainty
TL;DR: We propose a novel OOD detector that employ blurred images as adversarial examples . Our model achieve significant OOD detection performance in various domains.
Abstract: Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) are known to assign lower uncertainty to the OOD data than the target distribution. In this work, we discover that such conventional novelty detection schemes are also vulnerable to the blurred images. Based on the observation, we construct a novel RND-based OOD detector, SVD-RND, that utilizes blurred images during training. Our detector is simple, efficient in test time, and outperforms baseline OOD detectors in various domains. Further results show that SVD-RND learns a better target distribution representation than the baselines. Finally, SVD-RND combined with geometric transform achieves near-perfect detection accuracy in CelebA domain.