Metric Learning for Novelty and Anomaly Detection

Abstract

When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works.

arXiv commentAccepted at BMVC 2018, 10 pages main article and 4 pages supplementary material

References in corpus (4)

• 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
• Learning Deep Embeddings with Histogram Loss
• Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

Cited by in corpus (18)

• Recent Advances in Open Set Recognition: A Survey
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Student-Teacher Feature Pyramid Matching for Anomaly Detection
• What Do Compressed Deep Neural Networks Forget?
• Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
• Characterising Bias in Compressed Models
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching
• Semantic Drift Compensation for Class-Incremental Learning
• Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching
• Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder
• One Versus all for deep Neural Network Incertitude (OVNNI) quantification
• Out-of-Distribution Detection for Skin Lesion Images with Deep Isolation Forest
• Streaming Adaptive Nonparametric Variational Autoencoder
• Toward Metrics for Differentiating Out-of-Distribution Sets
• Unsupervised Anomaly Detection From Semantic Similarity Scores
• Multi-Class Anomaly Detection
• Multi-class Novelty Detection Using Mix-up Technique