History-Based Anomaly Detector: An Adversarial Approach to Anomaly Detection

Chatillon, Pierrick; Ballester, Coloma

doi:10.1007/978-3-030-55180-3_58

Cited by 4 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some methods consider the generation of pseudo-anomalous data. Data immaturely generated during the training process of GANs have been used as pseudo-anomalous data for training [33]- [35]. In CutPaste [36], patches of random sizes and angles are cut out from an image and randomly pasted onto the image.…”

Section: Pseudo-anomalous Datamentioning

confidence: 99%

ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables

Murase

Fukumizu

2022

IEEE Access

View full text Add to dashboard Cite

In many anomaly detection tasks, where anomalous data rarely appear and are difficult to collect, training using only normal data is important. Although it is possible to manually create anomalous data using prior knowledge, they may be subject to user bias. In this paper, we propose an Anomalous Latent variable Generative Adversarial Network (ALGAN) in which the GAN generator produces pseudo-anomalous data as well as fake-normal data, whereas the discriminator is trained to distinguish between normal and pseudo-anomalous data. This differs from the standard GAN discriminator, which specializes in classifying two similar classes. The training dataset contains only normal data; the latent variables are introduced in anomalous states and are input into the generator to produce diverse pseudoanomalous data. We compared the performance of ALGAN with other existing methods on the MVTec-AD, Magnetic Tile Defects, and COIL-100 datasets. The experimental results showed that ALGAN exhibited an AUROC comparable to those of state-of-the-art methods while achieving a much faster prediction time.

show abstract

Section: Pseudo-anomalous Datamentioning

confidence: 99%

ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables

Murase

Fukumizu

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Outlier Exposure Based Approaches Utilizing the fake data for the novelty detection task has previously been considered. The general idea is to employ synthetic images, which may be generated by GANs, to augment the training set [28][29][30][31][32]. In the case of open-set recognition, [9] proposed OpenGAN, which adverserially generates fake open-set images.…”

Section: Comparisons With State-of-the-artmentioning

confidence: 99%

Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection

Mirzaei¹,

Salehi²,

Shahabi³

et al. 2022

Preprint

View full text Add to dashboard Cite

We aim for image-based novelty detection. Despite considerable progress, existing models either fail or face a dramatic drop under the so-called "near-distribution" setting, where the differences between normal and anomalous samples are subtle. We first demonstrate existing methods experience up to 20% decrease in performance in the near-distribution setting. Next, we propose to exploit a scorebased generative model to produce synthetic near-distribution anomalous data. Our model is then fine-tuned to distinguish such data from the normal samples. We provide a quantitative as well as qualitative evaluation of this strategy, and compare the results with a variety of GAN-based models. Effectiveness of our method for both the near-distribution and standard novelty detection is assessed through extensive experiments on datasets in diverse applications such as medical images, object classification, and quality control. This reveals that our method considerably improves over existing models, and consistently decreases the gap between the near-distribution and standard novelty detection performance. Overall, our method improves the near-distribution novelty detection by 6% and passes the state-of-the-art by 1% to 5% across nine novelty detection benchmarks. The code repository is available at https://github.com/rohban-lab/FITYMI.

show abstract

Anomaly detection methods based on GAN: a survey

Li²

2022

Appl Intell

View full text Add to dashboard Cite

History-Based Anomaly Detector: An Adversarial Approach to Anomaly Detection

Cited by 4 publications

References 31 publications

ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables

ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables

Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection

Anomaly detection methods based on GAN: a survey

Contact Info

Product

Resources

About