Toward Deep Supervised Anomaly Detection: Reinforcement Learning from
Partially Labeled Anomaly Data
- URL: http://arxiv.org/abs/2009.06847v2
- Date: Thu, 10 Jun 2021 13:40:11 GMT
- Title: Toward Deep Supervised Anomaly Detection: Reinforcement Learning from
Partially Labeled Anomaly Data
- Authors: Guansong Pang, Anton van den Hengel, Chunhua Shen, Longbing Cao
- Abstract summary: We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset.
Existing related methods either exclusively fit the limited anomaly examples that typically do not span the entire set of anomalies, or proceed with unsupervised learning from the unlabeled data.
We propose here instead a deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies.
- Score: 150.9270911031327
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We consider the problem of anomaly detection with a small set of partially
labeled anomaly examples and a large-scale unlabeled dataset. This is a common
scenario in many important applications. Existing related methods either
exclusively fit the limited anomaly examples that typically do not span the
entire set of anomalies, or proceed with unsupervised learning from the
unlabeled data. We propose here instead a deep reinforcement learning-based
approach that enables an end-to-end optimization of the detection of both
labeled and unlabeled anomalies. This approach learns the known abnormality by
automatically interacting with an anomaly-biased simulation environment, while
continuously extending the learned abnormality to novel classes of anomaly
(i.e., unknown anomalies) by actively exploring possible anomalies in the
unlabeled data. This is achieved by jointly optimizing the exploitation of the
small labeled anomaly data and the exploration of the rare unlabeled anomalies.
Extensive experiments on 48 real-world datasets show that our model
significantly outperforms five state-of-the-art competing methods.
Related papers
- Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data [31.029029510114448]
Existing semi-supervised approaches assume that unlabeled data are mostly normal.
We propose the positive-unlabeled autoencoder, which is based on positive-unlabeled learning and the anomaly detector such as the autoencoder.
Our approach achieves better detection performance than existing approaches.
arXiv Detail & Related papers (2024-05-29T09:34:47Z) - Anomaly Detection by Context Contrasting [57.695202846009714]
Anomaly Detection focuses on identifying samples that deviate from the norm.
Recent advances in self-supervised learning have shown great promise in this regard.
We propose Con2, which addresses this problem by setting normal training data into distinct contexts.
Our approach achieves state-of-the-art performance on various benchmarks while exhibiting superior performance in a more realistic healthcare setting.
arXiv Detail & Related papers (2024-05-29T07:59:06Z) - SaliencyCut: Augmenting Plausible Anomalies for Anomaly Detection [24.43321988051129]
We propose a novel saliency-guided data augmentation method, SaliencyCut, to produce pseudo but more common anomalies.
We then design a novel patch-wise residual module in the anomaly learning head to extract and assess the fine-grained anomaly features from each sample.
arXiv Detail & Related papers (2023-06-14T08:55:36Z) - AGAD: Adversarial Generative Anomaly Detection [12.68966318231776]
Anomaly detection suffered from the lack of anomalies due to the diversity of abnormalities and the difficulties of obtaining large-scale anomaly data.
We propose Adversarial Generative Anomaly Detection (AGAD), a self-contrast-based anomaly detection paradigm.
Our method generates pseudo-anomaly data for both supervised and semi-supervised anomaly detection scenarios.
arXiv Detail & Related papers (2023-04-09T10:40:02Z) - Catching Both Gray and Black Swans: Open-set Supervised Anomaly
Detection [90.32910087103744]
A few labeled anomaly examples are often available in many real-world applications.
These anomaly examples provide valuable knowledge about the application-specific abnormality.
Those anomalies seen during training often do not illustrate every possible class of anomaly.
This paper tackles open-set supervised anomaly detection.
arXiv Detail & Related papers (2022-03-28T05:21:37Z) - SLA$^2$P: Self-supervised Anomaly Detection with Adversarial
Perturbation [77.71161225100927]
Anomaly detection is a fundamental yet challenging problem in machine learning.
We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
arXiv Detail & Related papers (2021-11-25T03:53:43Z) - Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
We introduce a novel weakly-supervised anomaly detection framework to train detection models.
The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability.
Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
arXiv Detail & Related papers (2021-08-01T14:33:17Z) - Deep Weakly-supervised Anomaly Detection [118.55172352231381]
Pairwise Relation prediction Network (PReNet) learns pairwise relation features and anomaly scores.
PReNet can detect any seen/unseen abnormalities that fit the learned pairwise abnormal patterns.
Empirical results on 12 real-world datasets show that PReNet significantly outperforms nine competing methods in detecting seen and unseen anomalies.
arXiv Detail & Related papers (2019-10-30T00:40:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.