A curated list of awesome anomaly detection resources. Inspired by awesome-architecture-search and awesome-automl.
Last updated: 2019/01/16
Anomaly detection is a technique used to identify unusual patterns that do not conform to expected behavior, called outliers. Typically, this is treated as an unsupervised learning problem where the anomalous samples are not known a priori and it is assumed that the majority of the training dataset consists of “normal” data (here and elsewhere the term “normal” means not anomalous and is unrelated to the Gaussian distribution). [Lukas Ruff et al., 2018; Deep One-Class Classification]
In general, Anomaly detection is also called Novelty Detection or Outlier Detection, Forgery Detection and Out-of-distribution Detection.
Each term has slightly different meanings. Mostly, on the assumption that you do not have unusual data, this problem is especially called One Class Classification, One Class Segmentation.
Also, there are two types of target data. (time-series data, and image data)
In time-series data, it is aimed to detect a abnormal sections or frames in input data. (ex, videos, signal, etc)
In image data, it is aimed to classify abnormal images or to segment abnormal regions, for example, defect in some manufacturing data.
- Anomaly Detection of Time Series | Deepthi Cheboli | [Thesis' 10] |
[pdf] - Long short term memory networks for anomaly detection in time series | Pankaj Malhotra
et al. | [ESANN' 15] |
[pdf] - Time Series Anomaly Detection; Detection of anomalous drops with limited features and sparse examples in noisy highly periodic data | Dominique T. Shipmon, et al. | [arXiv' 17] |
[pdf] - Abnormal Event Detection in Videos using Spatiotemporal Autoencoder | Yong Shean Chong, et al. | [ISNN' 17] |
[pdf] - Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis | Doyup Lee | [ICMLA' 17] |
[pdf] - Real-world Anomaly Detection in Surveillance Videos | Waqas Sultani, et al. | [arXiv' 18] |
[pdf][project page] - Unsupervised Anomaly Detection for Traffic Surveillance Based on Background Modeling | JiaYi Wei, et el. | [CVPR Workshop' 18] |
[pdf] - Dual-Mode Vehicle Motion Pattern Learning for High Performance Road Traffic Anomaly Detection | Yan Xu, et el. | [CVPR Workshop' 18] |
[pdf]
- Estimating the Support of a High- Dimensional Distribution [OC-SVM] | Bernhard Schölkopf, et al. | [Journal of Neural Computation' 01] |
[pdf] - A Survey of Recent Trends in One Class Classification | Shehroz S, et al. | [AICS' 09] |
[pdf] - Anomaly detection using au- toencoders with nonlinear dimensionality reduction | Mayu Sakurada, et al. | [MLSDA Workshop' 14] |
[link] - A review of novelty detection | Marco A. F Pimentel et al. | [Signal Processing' 14] |
[link] - Variational Autoencoder based Anomaly Detection using Reconstruction Probability | Jinwon An, Sungzoon Cho | [SNU DMC Tech' 15] |
[pdf] - High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning | Sarah M. Erfani, et al. | [Pattern Recognition' 16] |
[link] - Transfer Representation-Learning for Anomaly Detection | Jerone T. A. Andrews, et al. | [ICML' 16] |
[pdf] - A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks | Dan Hendrycks, Kevin Gimpel | [ICLR' 17] |
[pdf] - Outlier Detection with Autoencoder Ensembles | Chen, J, et al. | [SDM' 17] |
[pdf] - Provable self-representation based outlier detection in a union of subspaces | Chong You, et al. | [CVPR' 17] |
[pdf] - Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks [ODIN] | Shiyu Liang, et al. | [ICLR' 18] |
[pdf] - Learning Confidence for Out-of-Distribution Detection in Neural Networks | Terrance DeVries, et al. | [arXiv' 18] |
[pdf] - Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples | Kimin Lee, et al. | [ICLR' 18] |
[pdf] - Adversarially Learned One-Class Classifier for Novelty Detection [ALOCC] | Mohammad Sabokrou, et al. | [CVPR' 18] |
[pdf][code] - Learning Deep Features for One-Class Classification | Pramuditha Perera, et al. | [arXiv' 18] |
[pdf][code] - Efficient GAN-Based Anomaly Detection | Houssam Zenati, et al. | [arXiv' 18] |
[pdf] - Hierarchical Novelty Detection for Visual Object Recognition | Kibok Lee, et al. | [CVPR' 18] |
[pdf] - Deep One-Class Classification | Lukas Ruff, el al. | [ICML' 18] |
[pdf] - Reliably Decoding Autoencoders’ Latent Spaces for One-Class Learning Image Inspection Scenarios | Daniel Soukup, Thomas Pinetz | [OAGM Workshop' 18] |
[pdf] - q-Space Novelty Detection with Variational Autoencoders | Aleksei Vasilev, et al. | [arXiv' 18] |
[pdf] - GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training | Samet Akcay, et al. | [ACCV' 18] |
[pdf] - Out-of-Distribution Detection using Multiple Semantic Label Representations | Gabi Shalev, et al. | [NIPS' 18] |
[pdf] - Deep Anomaly Detection Using Geometric Transformations | Izhak Golan, et al. | [NIPS' 18] |
[pdf] - Generative Probabilistic Novelty Detection with Adversarial Autoencoders | Stanislav Pidhorskyi, et al. | [NIPS' 18] |
[pdf] - A loss framework for calibrated anomaly detection | Aditya Krishna Menon, et al. | [NIPS' 18] |
[pdf] - A Practical Algorithm for Distributed Clustering and Outlier Detection | Jiecao Chen, et al. | [NIPS' 18] |
[pdf] - Efficient Anomaly Detection via Matrix Sketching | Vatsal Sharan, et al. | [NIPS' 18] |
[pdf] - A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks | Kimin Lee, et al. | [NIPS' 18] |
[pdf] - Deep Anomaly Detection with Outlier Exposure | Dan Hendrycks, et al. | [ICLR' 19] |
[pdf]
- Anomaly Detection and Localization in Crowded Scenes | Weixin Li, et al. | [TPAMI' 14] |
[pdf] - Novelty detection in images by sparse representations | Giacomo Boracchi, et al. | [IEEE Symposium on IES' 14] |
[link] - Detecting anomalous structures by convolutional sparse models | Diego Carrera, et al. | [IJCNN' 15] |
[pdf] - Real-Time Anomaly Detection and Localization in Crowded Scenes | Mohammad Sabokrou, et al. | [CVPR Workshop' 15] |
[pdf] - Learning Deep Representations of Appearance and Motion for Anomalous Event Detection | Dan Xu, et al. | [BMVC' 15] |
[pdf] - Scale-invariant anomaly detection with multiscale group-sparse models | Diego Carrera, et al. | [IEEE ICIP' 16] |
[link] - Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery [AnoGAN] | Thomas Schlegl, et al. | [IPMI' 17] |
[pdf] - Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes | Mohammad Sabokrou, et al. | [Journal of Computer Vision and Image Understanding' 17] |
[pdf] - Anomaly Detection using a Convolutional Winner-Take-All Autoencoder | Hanh T. M. Tran, et al. | [BMVC' 17] |
[pdf] - Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity | Paolo Napoletano, et al. | [Sensors' 17] |
[pdf] - Defect Detection in SEM Images of Nanofibrous Materials | Diego Carrera, et al. | [IEEE Trans. on Industrial Informatics' 17] |
[pdf] - Abnormal event detection in videos using generative adversarial nets | Mahdyar Ravanbakhsh, et al. | [ICIP' 17] |
[link] - An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos | B Ravi Kiran, et al. | [arXiv' 18] |
[pdf] - Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders | Paul Bergmann, et al. | [arXiv' 18] |
[pdf] - Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier | Sri Kalyan Yarlagadda, et al. | [IS&T EI' 18] |
[pdf] - Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images | Christoph Baur, et al. | [arXiv' 18] |
[pdf]
If you have any suggenstions about papers, feel free to mail me :)