Unsupervised Anomaly Detection From Semantic Similarity Scores

The approach is based on learning a semantic similarity measure to find for a given test example the semantically closest example in the training set and then using a discriminator to classify whether the two examples show sufficient semantic dissimilarity such that the test example can be rejected as OOD. We are able to outperform previous approaches for anomaly, novelty, or out-of-distribution detection in the visual domain by a large margin. In particular we obtain AUROC values close to one for the challenging task of detecting examples from CIFAR-10 as out-of-distribution given CIFAR-100 as in-distribution, without making use of label information. Anomaly detection or novelty detection aims at identifying patterns in data that are significantly different to what is expected. This problem is inherently a binary classification problem that classifies examples either as in-distribution or out-of-distribution, given a sufficiently large sample from the in-distribution (training set). A natural approach to OOD detection is to learn a density model from the training data and compute the likelihood ratio of OOD examples to in-distribution examples.