Novelty Detection Via Blurring
This addresses a specific vulnerability in novelty detection for machine learning systems, but it is incremental as it builds on existing RND methods.
The paper tackled the problem of out-of-distribution detection being vulnerable to blurred images, resulting in a novel RND-based detector called SVD-RND that outperforms baselines and achieves near-perfect accuracy on the CelebA dataset.
Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) have been observed to assign lower uncertainty to the OOD 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 at test time, and outperforms baseline OOD detectors in various domains. Further results show that SVD-RND learns better target distribution representation than the baseline RND algorithm. Finally, SVD-RND combined with geometric transform achieves near-perfect detection accuracy on the CelebA dataset.