Novelty Detection Via Blurring

Abstract

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.

ICLR 2020

References in corpus (14)

• Auto-Encoding Variational Bayes
• Neural Discrete Representation Learning
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Deep Learning for Anomaly Detection: A Survey
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• AutoAugment: Learning Augmentation Policies from Data
• Efficient GAN-Based Anomaly Detection
• Deep Anomaly Detection with Outlier Exposure
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
• Deep Semi-Supervised Anomaly Detection
• Out-of-Distribution Detection using Multiple Semantic Label Representations

Cited by in corpus (6)

• Generalized Out-of-Distribution Detection: A Survey
• DeepLens: Interactive Out-of-distribution Data Detection in NLP Models
• Elsa: Energy-based learning for semi-supervised anomaly detection
• Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
• Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion
• Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection