# Novelty Detection Via Blurring

arXiv: https://arxiv.org/abs/1911.11943 · HTML: https://mlsanity.com/paper/1911.11943/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2019.

## Built on by (most cited first, 24 of 24)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Watermarking for Out-of-distribution Detection](https://mlsanity.com/paper/2210.15198/) (2022)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation](https://mlsanity.com/paper/2502.05780/) (2025)
- [3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds](https://mlsanity.com/paper/2207.11554/) (2022)
- [Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models](https://mlsanity.com/paper/2312.02615/) (2023)
- [Task Agnostic and Post-hoc Unseen Distribution Detection](https://mlsanity.com/paper/2207.13083/) (2022)
- [Exploiting Diffusion Prior for Out-of-Distribution Detection](https://mlsanity.com/paper/2406.11105/) (2024)
- [Elsa: Energy-based learning for semi-supervised anomaly detection](https://mlsanity.com/paper/2103.15296/) (2021)
- [Data Invariants to Understand Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/2111.13362/) (2021)
- [DeepLens: Interactive Out-of-distribution Data Detection in NLP Models](https://mlsanity.com/paper/2303.01577/) (2023)
- [Data refinement for fully unsupervised visual inspection using pre-trained networks](https://mlsanity.com/paper/2202.12759/) (2022)
- [Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection](https://mlsanity.com/paper/2106.01277/) (2021)
- [Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling](https://mlsanity.com/paper/2201.06378/) (2022)
- [Bridging In- and Out-of-distribution Samples for Their Better Discriminability](https://mlsanity.com/paper/2101.02500/) (2021)
- [Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models](https://mlsanity.com/paper/2106.07903/) (2021)
- [Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion](https://mlsanity.com/paper/2305.03098/) (2023)
- [Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning](https://mlsanity.com/paper/2408.10676/) (2024)
- [What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition](https://mlsanity.com/paper/2605.13032/) (2026)
- [Pediatric Otoscopy Video Screening with Shift Contrastive Anomaly Detection](https://mlsanity.com/paper/2110.13254/) (2021)
- [The Exponentially Tilted Gaussian Prior for Variational Autoencoders](https://mlsanity.com/paper/2111.15646/) (2021)
- [WeShort: Out-of-distribution Detection With Weak Shortcut structure](https://mlsanity.com/paper/2207.05055/) (2022)
- [Be Bayesian by Attachments to Catch More Uncertainty](https://mlsanity.com/paper/2310.13027/) (2023)
- [Revisiting Energy-Based Model for Out-of-Distribution Detection](https://mlsanity.com/paper/2412.03058/) (2024)

## Abstract (arXiv)

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.