AVID: Adversarial Visual Irregularity Detection

by   Mohammad Sabokrou, et al.

Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc. With the surge of deep learning methods in the recent years, researchers have tried a wide spectrum of methods for different applications. However, for the case of irregularity or anomaly detection in videos, training an end-to-end model is still an open challenge, since often irregularity is not well-defined and there are not enough irregular samples to use during training. In this paper, inspired by the success of generative adversarial networks (GANs) for training deep models in unsupervised or self-supervised settings, we propose an end-to-end deep network for detection and fine localization of irregularities in videos (and images). Our proposed architecture is composed of two networks, which are trained in competing with each other while collaborating to find the irregularity. One network works as a pixel-level irregularity Inpainter, and the other works as a patch-level Detector. After an adversarial self-supervised training, in which I tries to fool D into accepting its inpainted output as regular (normal), the two networks collaborate to detect and fine-segment the irregularity in any given testing video. Our results on three different datasets (one synthetic and two video datasets) show that our proposed method can not only outperform the state-of-the-art but also to fine-segment the irregularity.


page 2

page 8

page 9

page 12


Adversarially Learned One-Class Classifier for Novelty Detection

Novelty detection is the process of identifying the observation(s) that ...

End-to-End Adversarial Learning for Intrusion Detection in Computer Networks

This paper presents a simple yet efficient method for an anomaly-based I...

History-based Anomaly Detector: an Adversarial Approach to Anomaly Detection

Anomaly detection is a difficult problem in many areas and has recently ...

DATE: Detecting Anomalies in Text via Self-Supervision of Transformers

Leveraging deep learning models for Anomaly Detection (AD) has seen wide...

Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds

Abnormal crowd behaviour detection attracts a large interest due to its ...

Self-Supervised Representation Learning via Neighborhood-Relational Encoding

In this paper, we propose a novel self-supervised representation learnin...

Please sign up or login with your details

Forgot password? Click here to reset