One-Class Classification: A Survey

TLDR

One‑class classification trains on a single positive class and has attracted significant interest in computer vision, machine learning, and biometrics. This survey reviews classical statistical and deep learning OCC methods for visual recognition, evaluates their strengths and weaknesses, and outlines future research directions while summarizing datasets and evaluation metrics. The authors survey classical statistical and deep learning OCC approaches, assess their merits and drawbacks, and discuss commonly used datasets and evaluation metrics.

Abstract

One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class. The goal of OCC is to learn a representation and/or a classifier that enables recognition of positively labeled queries during inference. This topic has received considerable amount of interest in the computer vision, machine learning and biometrics communities in recent years. In this article, we provide a survey of classical statistical and recent deep learning-based OCC methods for visual recognition. We discuss the merits and drawbacks of existing OCC approaches and identify promising avenues for research in this field. In addition, we present a discussion of commonly used datasets and evaluation metrics for OCC.