An Outlier Exposure Approach to Improve Visual Anomaly Detection Performance for Mobile Robots

Abstract

We consider the problem of building visual anomaly detection systems for mobile robots. Standard anomaly detection models are trained using large datasets composed only of non-anomalous data. However, in robotics applications, it is often the case that (potentially very few) examples of anomalies are available. We tackle the problem of exploiting these data to improve the performance of a Real-NVP anomaly detection model, by minimizing, jointly with the Real-NVP loss, an auxiliary outlier exposure margin loss. We perform quantitative experiments on a novel dataset (which we publish as supplementary material) designed for anomaly detection in an indoor patrolling scenario. On a disjoint test set, our approach outperforms alternatives and shows that exposing even a small number of anomalous frames yields significant performance improvements.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• A Unifying Review of Deep and Shallow Anomaly Detection
• Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
• The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
• Safe Robot Navigation via Multi-Modal Anomaly Detection
• Perceptual Image Anomaly Detection
• Sensing Anomalies as Potential Hazards: Datasets and Benchmarks