Beyond the Known: Adversarial Autoencoders in Novelty Detection

arXiv:2404.04456v1 Announce Type: cross
Abstract: In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with …

abstract adversarial arxiv autoencoders beyond cs.ai cs.cv cs.lg data dataset decoder detection distribution encoder error frameworks network outlier training type