G2D: Generate to Detect Anomaly - Université de technologie de Troyes Access content directly
Conference Papers Year : 2021

G2D: Generate to Detect Anomaly


In this paper, we propose a novel method for irregularity detection. Previous researches solve this problem as a One-Class Classification (OCC) task where they train a reference model on all of the available samples. Then, they consider a test sample as an anomaly if it has a diversion from the reference model. Generative Adversarial Networks (GANs) have achieved the most promising results for OCC while implementing and training such networks, especially for the OCC task, is a cumbersome and computationally expensive procedure. To cope with the mentioned challenges, we present a simple but effective method to solve the irregularity detection as a binary classification task in order to make the implementation easier along with improving the detection performance. We learn two deep neural networks (generator and discriminator) in a GAN-style setting on merely the normal samples. During training, the generator gradually becomes an expert to generate samples which are similar to the normal ones. In the training phase, when the generator fails to produce normal data (in the early stages of learning and also prior to the complete convergence), it can be considered as an irregularity generator. In this way, we simultaneously generate the irregular samples. Afterward, we train a binary classifier on the generated anomalous samples along with the normal instances in order to be capable of detecting irregularities. The proposed framework applies to different related applications of outlier and anomaly detection in images and videos, respectively. The results confirm that our proposed method is superior to the baseline and state-of-the-art solutions.

Dates and versions

hal-03320693 , version 1 (16-08-2021)



Masoud Pourreza, Bahram Mohammadi, Mostafa Khaki, Samir Bouindour, Hichem Snoussi, et al.. G2D: Generate to Detect Anomaly. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Jan 2021, Waikoloa, United States. pp.2002-2011, ⟨10.1109/WACV48630.2021.00205⟩. ⟨hal-03320693⟩
27 View
0 Download



Gmail Mastodon Facebook X LinkedIn More