Abstract
Novelty detection is a process for distinguishing the observations that differ in some respect from the observations that the model is trained on. Novelty detection is one of the fundamental requirements of a good classification or identification system since sometimes the test data contains observations that were not known at the training time. In other words, the novelty class is often is not presented during the training phase or not well defined. In light of the above, one-class classifiers and generative methods can efficiently model such problems. However, due to the unavailability of data from the novelty class, training an end-to-end model is a challenging task itself. Therefore, detecting the Novel classes in unsupervised and semi-supervised settings is a crucial step in such tasks. In this thesis, we propose several methods to model the novelty detection problem in unsupervised and semi-supervised fashion. The proposed frameworks applied to different related applications of anomaly and outlier detection tasks. The results show the superior of our proposed methods in compare to the baselines and state-of-the-art methods.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1904.04741