Anomaly Detection using One-Class Neural Networks

Chalapathy, Raghavendra; Menon, Aditya Krishna; Chawla, Sanjay

doi:10.48550/arxiv.1802.06360

Cited by 110 publications

(172 citation statements)

References 0 publications

Supporting

Mentioning

172

Contrasting

Order By: Relevance

“…To address this issue, recent work [5], [7], [22], [23], [24], [25], [26], [27] focuses on coupling the representation learning objective with anomaly detection. For example, deep distance-based methods [5], [23] integrate the representation learning with distance-based anomaly detectors, while deep one-class classifiers, such as deep support vector data description (SVDD) [7], [22], [27] and deep one-class SVM [25], [26], aim to learn representations for the one-class classification model. These approaches achieve large improvement over the previous methods.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Deep Anomaly Detection with Deviation Networks

Pang

Shen

Hengel

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

289

168

View full text Add to dashboard Cite

Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new feature representations to enable downstream anomaly detection methods, perform indirect optimization of anomaly scores, leading to data-inefficient learning and suboptimal anomaly scoring. Also, they are typically designed as unsupervised learning due to the lack of large-scale labeled anomaly data. As a result, they are difficult to leverage prior knowledge (e.g., a few labeled anomalies) when such information is available as in many real-world anomaly detection applications.This paper introduces a novel anomaly detection framework and its instantiation to address these problems. Instead of representation learning, our method fulfills an end-to-end learning of anomaly scores by a neural deviation learning, in which we leverage a few (e.g., multiple to dozens) labeled anomalies and a prior probability to enforce statistically significant deviations of the anomaly scores of anomalies from that of normal data objects in the upper tail. Extensive results show that our method can be trained substantially more data-efficiently and achieves significantly better anomaly scoring than state-of-the-art competing methods.

show abstract

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Deep Anomaly Detection with Deviation Networks

Pang

Shen

Hengel

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

289

168

View full text Add to dashboard Cite

show abstract

“…OOD detection has been a long history. Most existing works are in supervised representations (Liang, Li, and Srikant 2017;Chalapathy, Menon, and Chawla 2018;Lee et al 2018;Hendrycks and Gimpel 2016;Hendrycks, Mazeika, and Dietterich 2019). These algorithms train a model that produces a score indicating how likely the input sample is an inlier.…”

Section: Out-of-distribution Detectionmentioning

confidence: 99%

Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task

Chen¹,

Zhu²,

Dai³

2021

Preprint

View full text Add to dashboard Cite

Self-supervised learning (SSL) has achieved great success in a variety of computer vision tasks. However, the mechanism of how SSL works in these tasks remains a mystery. In this paper, we study how SSL can enhance the performance of the out-of-distribution (OOD) detection task. We first point out two general properties that a good OOD detector should have: 1) the overall feature space should be large and 2) the inlier feature space should be small. Then we demonstrate that SSL can indeed increase the intrinsic dimension of the overall feature space. In the meantime, SSL even has the potential to shrink the inlier feature space. As a result, there will be more space spared for the outliers, making OOD detection much easier. The conditions when SSL can shrink the inlier feature space is also discussed and validated. By understanding the role of SSL in the OOD detection task, our study can provide a guideline for designing better OOD detection algorithms. Moreover, this work can also shed light to other tasks where SSL can improve the performance.

show abstract

“…The difference between the original test image and the reconstruction indicates anomalies in the image. There are different methods to learn the normality of data such as autoencoders and their variants ( [5], [15], [16], [17]), one-class SVMs ( [18], [19]), and generative adversarial network ( [20], [21]). These methods cannot incorporate the context for learning the normality.…”

Section: A Related Workmentioning

confidence: 99%

“…We compare CADNet with several approaches, including a standard autoencoder [16], one-class SVM [18], and GAN [20], to learn normality. For the sake of compatibility, we implement these baselines with the same architecture of the encoder-decoder parts of CADNet.…”

Section: Baselinesmentioning

confidence: 99%

Context-Dependent Anomaly Detection for Low Altitude Traffic Surveillance

Bozcan¹,

Kayacan²

2021

Preprint

View full text Add to dashboard Cite

The detection of contextual anomalies is a challenging task for surveillance since an observation can be considered anomalous or normal in a specific environmental context. An unmanned aerial vehicle (UAV) can utilize its aerial monitoring capability and employ multiple sensors to gather contextual information about the environment and perform contextual anomaly detection. In this work, we introduce a deep neural network-based method (CADNet) to find point anomalies (i.e., single instance anomalous data) and contextual anomalies (i.e., context-specific abnormality) in an environment using a UAV. The method is based on a variational autoencoder (VAE) with a context sub-network. The context sub-network extracts contextual information regarding the environment using GPS and time data, then feeds it to the VAE to predict anomalies conditioned on the context. To the best of our knowledge, our method is the first contextual anomaly detection method for UAV-assisted aerial surveillance. We evaluate our method on the AU-AIR dataset in a traffic surveillance scenario. Quantitative comparisons against several baselines demonstrate the superiority of our approach in the anomaly detection tasks. The codes and data will be available at https://bozcani. github.io/cadnet.

show abstract

Anomaly Detection using One-Class Neural Networks

Cited by 110 publications

References 0 publications

Deep Anomaly Detection with Deviation Networks

Deep Anomaly Detection with Deviation Networks

Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task

Context-Dependent Anomaly Detection for Low Altitude Traffic Surveillance

Contact Info

Product

Resources

About