University of Oulu

M. Sabokrou, M. Fathy, G. Zhao and E. Adeli, "Deep End-to-End One-Class Classifier," in IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 675-684, Feb. 2021, doi: 10.1109/TNNLS.2020.2979049

Deep end-to-end one-class classifier

Saved in:
Author: Sabokrou, Mohammac1; Fathy, Mahmood1; Zhao, Guoying2;
Organizations: 1School of Computer Science, Institute for Research in Fundamental Science (IPM), Tehran 19395-5746, Iran
2Center for Machine Vision and Signal Analysis, University of Oulu, 90570 Oulu, Finland
3Department of Computer Science and the Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA 94305 USA
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.6 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-04-23


One-class classification (OCC) poses as an essential component in many machine learning and computer vision applications, including novelty, anomaly, and outlier detection systems. With a known definition for a target or normal set of data, one-class classifiers can determine if any given new sample spans within the distribution of the target class. Solving for this task in a general setting is particularly very challenging, due to the high diversity of samples from the target class and the absence of any supervising signal over the novelty (nontarget) concept, which makes designing end-to-end models unattainable. In this article, we propose an adversarial training approach to detect out-of-distribution samples in an end-to-end trainable deep model. To this end, we jointly train two deep neural networks, R and D. The latter plays as the discriminator while the former, during training, helps D characterize a probability distribution for the target class by creating adversarial examples and, during testing, collaborates with it to detect novelties. Using our OCC, we first test outlier detection on two image data sets, Modified National Institute of Standards and Technology (MNIST) and Caltech-256. Then, several experiments for video anomaly detection are performed on University of Minnesota (UMN) and University of California, San Diego (UCSD) data sets. Our proposed method can successfully learn the target class underlying distribution and outperforms other approaches.

see all

Series: IEEE transactions on neural networks and learning systems
ISSN: 2162-237X
ISSN-E: 2162-2388
ISSN-L: 2162-237X
Volume: 32
Issue: 2
Pages: 675 - 684
DOI: 10.1109/TNNLS.2020.2979049
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Copyright information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.