• Corpus ID: 236772195

Explainable Deep Few-shot Anomaly Detection with Deviation Networks

  title={Explainable Deep Few-shot Anomaly Detection with Deviation Networks},
  author={Guansong Pang and Choubo Ding and Chunhua Shen and Anton van den Hengel},
Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples), assuming no access to any labeled anomaly data. One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train… 

Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection*

This paper proposes a novel approach that learns disentangled representations of abnormalities illustrated by seen anomalies, pseudo anomalies, and latent residual anomalies (i.e., samples that have unusual residuals compared to the normal data in a latent space), with the last two abnormalities designed to detect unseen anomalies.

Prototypical Residual Networks for Anomaly Detection and Localization

A framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions, is proposed.

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

This paper proposes a novel hierarchical semi-supervised contrastive learning (HSCL) framework, for contamination-resistant anomaly detection, which hierarchically regulates three complementary relations: sample-to-sample, sample- to-prototype, and normal-to -abnormal relations, enlarging the discrimination between normal and abnormal samples with a comprehensive exploration of the contaminated data.

Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Better Anomaly Detection

A carefully designed explicit boundary guided semi-push-pull learning strategy, which can enhance discriminability while mitigating bias problem caused by insufficient known anomalies and propose RandAugmented CutPaste which can simulate anomalies by creating local irregularities in normal samples to mitigate the insufficient of anomaly samples.

LesionPaste: One-Shot Anomaly Detection for Medical Images

A one-shot anomaly detection framework, namely LesionPaste, that utilizes true anomalies from a single annotated sample and synthesizes artificial anomalous samples for anomaly detection, which largely outperforms several state-of-the-art unsupervised and semi-supervised anomaly detection methods, and is on a par with the fully- supervised counterpart.

Explanation Method for Anomaly Detection on Mixed Numerical and Categorical Spaces

This work presents the extension EADMNC (Explainable Anomaly Detection on Mixed Numerical and Categorical spaces), which adds explainability to the predictions obtained with the original model, which preserved the scalability of the original method thanks to the Apache Spark framework.

Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples

A teacher-student structured model for 3D anomaly detection using feature space alignment, dimension zoom, and max pooling to extract the features of the point cloud and minimize a multi-scale loss between the feature vectors produced by the teacher and the student networks.

ADBench: Anomaly Detection Benchmark

This work conducts the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench, to identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design.

Trustworthy Anomaly Detection: A Survey

A summary of the existing efforts and open problems towards trustworthy anomaly detection from the perspectives of interpretability, fairness, robustness, and privacy-preservation are discussed.

A Survey on Explainable Anomaly Detection

A taxonomy based on the main aspects that characterize each explainable anomaly detection technique is proposed, aiming to help practitioners and researchers find the explainable detection method that best suits their needs.



Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data

A deep reinforcement learning-based approach that enables an end-to-end optimization of the detection of both labeled and unlabeled anomalies and significantly outperforms five state-of-the-art competing methods.

Deep Semi-Supervised Anomaly Detection

This work presents Deep SAD, an end-to-end deep methodology for general semi-supervised anomaly detection, and introduces an information-theoretic framework for deep anomaly detection based on the idea that the entropy of the latent distribution for normal data should be lower than the entropy the anomalous distribution, which can serve as a theoretical interpretation for the method.

Learning Memory-Guided Normality for Anomaly Detection

This work proposes to use a memory module with a new update scheme where items in the memory record prototypical patterns of normal data, boosting the discriminative power of both memory items and deeply learned features from normal data and lessening the representation capacity of CNNs.

Deep Anomaly Detection with Deviation Networks

A novel anomaly detection framework and its instantiation that can be trained substantially more data-efficiently and achieves significantly better anomaly scoring than state-of-the-art competing methods is introduced.

Margin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies

A Margin Learning Embedded Prediction (MLEP) framework that helps with the detection of abnormal events, even for anomalies that have never been previously observed, and pushes the application of anomaly detection towards real scenarios.

Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings

A powerful student-teacher framework for the challenging problem of unsupervised anomaly detection and pixel-precise anomaly segmentation in high-resolution images by trained to regress the output of a descriptive teacher network that was pretrained on a large dataset of patches from natural images.

Toward Supervised Anomaly Detection

It is argued that semi-supervised anomaly detection needs to ground on the unsupervised learning paradigm and devise a novel algorithm that meets this requirement and it is shown that the optimization problem has a convex equivalent under relatively mild assumptions.

A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

A hierarchical generative model is devised that captures the multi-scale patch distribution of each training image and demonstrates the superiority of this method on both the one-shot and few-shot settings, on the datasets of Paris, CIFAR10, MNIST and FashionMNIST as well as in the setting of defect detection on MVTec.

Adversarially Learned Anomaly Detection

This work proposes an anomaly detection method, Adversarially Learned Anomaly Detection (ALAD), that derives adversarially learned features for the anomaly detection task that achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.

Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

A novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos.