什么是异常检测?
异常检测是一种用于识别不符合预期行为的异常模式的技术,称为异常值。 通常,这被视为一个无监督学习问题,其中异常样本是先验未知的,并且假设训练数据集的大部分由“正常”数据组成(这里和其他地方的术语“正常”表示不异常并且是 与高斯分布无关)。 [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
.
and Novelty Detection
and Outlier Detection
have slightly different meanings. Figure below shows the differences of two terms.
此外,通常存在三种类型的目标数据。 (时间序列数据、图像数据、视频数据)
在时间序列数据中,旨在检测异常部分。 在图像、视频数据中,其目的是对异常图像进行分类或对异常区域进行分割,例如某些制造数据中的缺陷。
Survey Paper
- Deep Learning for Anomaly Detection: A Survey | [arXiv' 19] |
[pdf]
- Anomalous Instance Detection in Deep Learning: A Survey | [arXiv' 20] |
[pdf]
- Deep Learning for Anomaly Detection: A Review | [arXiv' 20] |
[pdf]
- A Unifying Review of Deep and Shallow Anomaly Detection | [arXiv' 20] |
[pdf]
- A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges | [arXiv' 21] |
[pdf]
Table of Contents
Time-series anomaly detection (need to survey more..)
- Anomaly Detection of Time Series | [Thesis' 10] |
[pdf]
- Long short term memory networks for anomaly detection in time series | [ESANN' 15] |
[pdf]
- LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems | [arXiv' 16] |
[pdf]
- Time Series Anomaly Detection; Detection of anomalous drops with limited features and sparse examples in noisy highly periodic data | [arXiv' 17] |
[pdf]
- Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis | [ICMLA' 17] |
[pdf]
- Truth Will Out: Departure-Based Process-Level Detection of Stealthy Attacks on Control Systems | [ACM CCS '18] |
[pdf]
- DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series | [IEEE Access' 18] |
[pdf]
- Time-Series Anomaly Detection Service at Microsoft | [KDD' 19] |
[pdf]
- Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network | [KDD' 19] |
[pdf]
- A Systematic Evaluation of Deep Anomaly Detection Methods for Time Series | Under Review |
[code]
- BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time | [IJCAI 19] |
[pdf]
- MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams | [AAAI' 20] |
[pdf]
|[code]
- Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network | [NeurIPS' 20]
- Anomaly Detection of Time Series With Smoothness-Inducing Sequential Variational Auto-Encoder | [TNNLS' 20]
Video-level anomaly detection
- Abnormal Event Detection in Videos using Spatiotemporal Autoencoder | [ISNN' 17] |
[pdf]
- Real-world Anomaly Detection in Surveillance Videos | [arXiv' 18] |
[pdf]
[project page]
- Unsupervised Anomaly Detection for Traffic Surveillance Based on Background Modeling | [CVPR Workshop' 18] |
[pdf]
- Dual-Mode Vehicle Motion Pattern Learning for High Performance Road Traffic Anomaly Detection | [CVPR Workshop' 18] |
[pdf]
- Detecting Abnormality without Knowing Normality: A Two-stage Approach for Unsupervised Video Abnormal Event Detection | [ACMMM' 18] |
[link]
- Motion-Aware Feature for Improved Video Anomaly Detection | [BMVC' 19] |
[pdf]
- Challenges in Time-Stamp Aware Anomaly Detection in Traffic Videos | [CVPRW' 19] |
[pdf]
- Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos | [CVPR' 19] |
[pdf]
- Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection | [CVPR'19] |
[pdf]
- Graph Embedded Pose Clustering for Anomaly Detection | [CVPR' 20] |
[pdf]
- Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly Detection | [CVPR' 20] |
[pdf]
- Learning Memory-Guided Normality for Anomaly Detection | [CVPR' 20] |
[pdf]
- Clustering-driven Deep Autoencoder for Video Anomaly Detection | [ECCV' 20] |
[pdf]
- CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection | [ECCV' 20] |
[pdf]
- Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events | [ACM MM' 20] |
[pdf]
|[code]
- A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels | [IEEE SPL' 20] |
[pdf]
- Few-Shot Scene-Adaptive Anomaly Detection | [ECCV' 20]
- Re Learning Memory Guided Normality for Anomaly Detection | [Arxiv' 20] |
[pdf]
- Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning | [ICCV' 21] |
[pdf]
|[code]
Image-level anomaly detection
One Class (Anomaly) Classification target
- Estimating the Support of a High- Dimensional Distribution [OC-SVM] | [Journal of Neural Computation' 01] |
[pdf]
- A Survey of Recent Trends in One Class Classification | [AICS' 09] |
[pdf]
- Anomaly detection using autoencoders with nonlinear dimensionality reduction | [MLSDA Workshop' 14] |
[link]
- A review of novelty detection | [Signal Processing' 14] |
[link]
- Variational Autoencoder based Anomaly Detection using Reconstruction Probability | [SNU DMC Tech' 15] |
[pdf]
- High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning | [Pattern Recognition' 16] |
[link]
- Transfer Representation-Learning for Anomaly Detection | [ICML' 16] |
[pdf]
- Outlier Detection with Autoencoder Ensembles | [SDM' 17] |
[pdf]
- Provable self-representation based outlier detection in a union of subspaces | [CVPR' 17] |
[pdf]
- [ALOCC]Adversarially Learned One-Class Classifier for Novelty Detection | [CVPR' 18] |
[pdf]
[code]
- Learning Deep Features for One-Class Classification | [arXiv' 18] |
[pdf]
[code]
- Efficient GAN-Based Anomaly Detection | [arXiv' 18] |
[pdf]
- Hierarchical Novelty Detection for Visual Object Recognition | [CVPR' 18] |
[pdf]
- Deep One-Class Classification | [ICML' 18] |
[pdf]
- Reliably Decoding Autoencoders’ Latent Spaces for One-Class Learning Image Inspection Scenarios | [OAGM Workshop' 18] |
[pdf]
- q-Space Novelty Detection with Variational Autoencoders | [arXiv' 18] |
[pdf]
- GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training | [ACCV' 18] |
[pdf]
- Deep Anomaly Detection Using Geometric Transformations | [NIPS' 18] |
[pdf]
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders | [NIPS' 18] |
[pdf]
[code]
- A loss framework for calibrated anomaly detection | [NIPS' 18] |
[pdf]
- A Practical Algorithm for Distributed Clustering and Outlier Detection | [NIPS' 18] |
[pdf]
- Efficient Anomaly Detection via Matrix Sketching | [NIPS' 18] |
[pdf]
- Adversarially Learned Anomaly Detection | [IEEE ICDM' 18] |
[pdf]
- Anomaly Detection With Multiple-Hypotheses Predictions | [ICML' 19] |
[pdf]
- Exploring Deep Anomaly Detection Methods Based on Capsule Net | [ICMLW' 19] |
[pdf]
- Latent Space Autoregression for Novelty Detection | [CVPR' 19] |
[pdf]
- OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations | [CVPR' 19] |
[pdf]
- Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training | [arXiv' 19] |
[pdf]
- Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty | [NeurIPS' 19] |
[pdf]
[code]
- Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network | [NeurIPS' 19] |
[pdf]
[code]
- Classification-Based Anomaly Detection for General Data | [ICLR' 20] |
[pdf]
- Robust Subspace Recovery Layer for Unsupervised Anomaly Detection | [ICLR' 20] |
[pdf]
- RaPP: Novelty Detection with Reconstruction along Projection Pathway | [ICLR' 20] |
[pdf]
- Novelty Detection Via Blurring | [ICLR' 20] |
[pdf]
- Deep Semi-Supervised Anomaly Detection | [ICLR' 20] |
[pdf]
- Robust anomaly detection and backdoor attack detection via differential privacy | [ICLR' 20] |
[pdf]
- Classification-Based Anomaly Detection for General Data | [ICLR' 20] |
[pdf]
- Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm | [CVPR' 20] |
[pdf]
- Deep End-to-End One-Class Classifier | [IEEE TNNLS' 20] |
[pdf]
- Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection | [ECCV' 20] |
[pdf]
- Backpropagated Gradient Representations for Anomaly Detection | [ECCV' 20]
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances | [NeurIPS' 20] |
[pdf]
|[code]
- Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework | [arXiv' 20] |
[pdf]
- Regularizing Attention Networks for Anomaly Detection in Visual Question Answering | [AAAI' 21] |
[pdf]
- Attribute Restoration Framework for Anomaly Detection | [IEEE Transactions on Multimedia 21] |
[pdf]
- Modeling the distribution of normal data in pre-trained deep features for anomaly detection | [ICPR' 20] |
[pdf]
|[code]
- Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection | [ICPR' 20] |
[pdf]
- Deep One-Class Classification via Interpolated Gaussian Descriptor | [arXiv' 21] |
[pdf]
|[code]
- Multiresolution Knowledge Distillation for Anomaly Detection | [CVPR' 21] |
[pdf]
|[code]
- Elsa: Energy-based learning for semi-supervised anomaly detection | [BMVC' 21] |
[pdf]
|[code]
Out-of-Distribution(OOD) Detection target
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks | [ICLR' 17] |
[pdf]
- [ODIN] Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks | [ICLR' 18] |
[pdf]
- Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples | [ICLR' 18] |
[pdf]
- Learning Confidence for Out-of-Distribution Detection in Neural Networks | [arXiv' 18] |
[pdf]
- Out-of-Distribution Detection using Multiple Semantic Label Representations | [NIPS' 18] |
[pdf]
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks | [NIPS' 18] |
[pdf]
- Metric Learning for Novelty and Anomaly Detection | [BMVC' 18] |
[pdf]
[code]
- Deep Anomaly Detection with Outlier Exposure | [ICLR' 19] |
[pdf]
- Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem | [CVPR' 19] |
[pdf]
- Outlier Exposure with Confidence Control for Out-of-Distribution Detection | [arXiv' 19] |
[pdf]
[code]
- Likelihood Ratios for Out-of-Distribution Detection | [NeurIPS' 19] |
[pdf]
- Outlier Detection in Contingency Tables Using Decomposable Graphical Models | [SJS' 19] |
[pdf]
[code]
- Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models | [ICLR' 20] |
[pdf]
- Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks | [ICML Workshop' 20] |
[pdf]
- Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data | [CVPR' 20] |
[pdf]
- A Boundary Based Out-Of-Distribution Classifier for Generalized Zero-Shot Learning | [ECCV' 20] |
[pdf]
- Provable Worst Case Guarantees for the Detection of Out-of-distribution Data | [NeurIPS' 20] |
[pdf]
|[code]
- On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law | [NeurIPS' 20] |
[pdf]
- Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder | [NeurIPS' 20] |
[pdf]
- OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification | [NeurIPS' 20]
- Energy-based Out-of-distribution Detection | [NeurIPS' 20] |
[pdf]
- Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples | [NeurIPS' 20]
- Why Normalizing Flows Fail to Detect Out-of-Distribution Data | [NeurIPS' 20] |
[pdf]
|[code]
- Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features | [NeurIPS' 20] |
[pdf]
- Further Analysis of Outlier Detection with Deep Generative Models | [NeurIPS' 20]
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances | [NeurIPS' 20] |
[pdf]
|[code]
- SSD: A Unified Framework for Self-Supervised Outlier Detection | [ICLR' 21]
[pdf]
|[code]
Unsupervised Anomaly Segmentation target
- Anomaly Detection and Localization in Crowded Scenes | [TPAMI' 14] |
[pdf]
- Novelty detection in images by sparse representations | [IEEE Symposium on IES' 14] |
[link]
- Detecting anomalous structures by convolutional sparse models | [IJCNN' 15] |
[pdf]
- Real-Time Anomaly Detection and Localization in Crowded Scenes | [CVPR Workshop' 15] |
[pdf]
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection | [BMVC' 15] |
[pdf]
- Scale-invariant anomaly detection with multiscale group-sparse models | [IEEE ICIP' 16] |
[link]
- [AnoGAN] Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery | [IPMI' 17] |
[pdf]
- Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes | [Journal of Computer Vision and Image Understanding' 17] |
[pdf]
- Anomaly Detection using a Convolutional Winner-Take-All Autoencoder | [BMVC' 17] |
[pdf]
- Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity | [Sensors' 17] |
[pdf]
- Defect Detection in SEM Images of Nanofibrous Materials | [IEEE Trans. on Industrial Informatics' 17] |
[pdf]
- Abnormal event detection in videos using generative adversarial nets | [ICIP' 17] |
[link]
- An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos | [arXiv' 18] |
[pdf]
- Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders | [arXiv' 18] |
[pdf]
- Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier | [IS&T EI' 18] |
[pdf]
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images | [arXiv' 18] |
[pdf]
- AVID: Adversarial Visual Irregularity Detection | [arXiv' 18] |
[pdf]
- MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection | [CVPR' 19] |
[pdf]
- Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT | [IEEE TMI' 19] |
[pdf]
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings | [CVPR' 20] |
[pdf]
- Attention Guided Anomaly Detection and Localization in Images | [ECCV' 20] |
[pdf]
- Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images | [ECCV' 20]
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences | [arXiv' 20] |
[pdf]
|[code]
- Patch SVDD, Patch-level SVDD for Anomaly Detection and Segmentation | [arXiv' 20] |
[pdf]
|[code]
- Unsupervised anomaly segmentation via deep feature reconstruction | [Neurocomputing' 20]|
[pdf]
|[code]
- PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization | [ICPR IML Workshop' 20]|
[pdf]
|[code]
- Explainable Deep One-Class Classification | [ICLR' 21]|
[pdf]
|[code]
- Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation | [arXiv' 21]
[pdf]
- Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images | [MICCAI' 21]|
[pdf]
|[code]
- Multiresolution Knowledge Distillation for Anomaly Detection | [CVPR' 21]|
[pdf]
原文:https://github.com/hoya012/awesome-anomaly-detection
- 登录 发表评论