Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is that of detecting the unknown/unseen anomaly case that takes us instead into the space of a one-class, semi-supervised learning paradigm. We introduce such a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space. Employing encoder-decoder-encoder sub-networks in the generator network enables the model to map the input image to a lower dimension vector, which is then used to reconstruct the generated output image. The use of the additional encoder network maps this generated image to its latent representation. Minimizing the distance between these images and the latent vectors during training aids in learning the data distribution for the normal samples. As a result, a larger distance metric from this learned data distribution at inference time is indicative of an outlier from that distribution—an anomaly. Experimentation over several benchmark datasets, from varying domains, shows the model efficacy and superiority over previous state-of-the-art approaches.

/pdf/ganomaly-semi-supervised-anomaly-detection-via-adversarial-2kjzyn0ubx.pdf

GANomaly : semi-supervised anomaly detection via adversarial training.

Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.

Deep Learning for Anomaly Detection: A Survey.

We present an efficient method for detecting anomalies in videos. Recent applications of convolutional neural networks have shown promises of convolutional layers for object detection and recognition, especially in images. However, convolutional neural networks are supervised and require labels as learning signals. We propose a spatiotemporal architecture for anomaly detection in videos including crowded scenes. Our architecture includes two main components, one for spatial feature representation, and one for learning the temporal evolution of the spatial features. Experimental results on Avenue, Subway and UCSD benchmarks confirm that the detection accuracy of our method is comparable to state-of-the-art methods at a considerable speed of up to 140 fps.

Abnormal Event Detection in Videos using Spatiotemporal Autoencoder

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.

A Unifying Review of Deep and Shallow Anomaly Detection

Deep learning approaches to anomaly detection (AD) have recently improved the state of the art in detection performance on complex data sets, such as large collections of images or text. These results have sparked a renewed interest in the AD problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review, we aim to identify the common underlying principles and the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic “shallow” and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that are enriched by the use of recent explainability techniques and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in AD.

/pdf/a-unifying-review-of-deep-and-shallow-anomaly-detection-61ph1bv9hs.pdf

Videos represent the primary source of information for surveillance applications. Video material is often available in large quantities but in most cases it contains little or no annotation for supervised learning. This article reviews the state-of-the-art deep learning based methods for video anomaly detection and categorizes them based on the type of model and criteria of detection. We also perform simple studies to understand the different approaches and provide the criteria of evaluation for spatio-temporal anomaly detection.

An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos

Videos represent the primary source of information for surveillance applications and are available in large amounts but in most cases contain little or no annotation for supervised learning. This article reviews the state-of-the-art deep learning based methods for video anomaly detection and categorizes them based on the type of model and criteria of detection. We also perform simple studies to understand the different approaches and provide the criteria of evaluation for spatio-temporal anomaly detection.

An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos

The complexity in visualizing volumetric data often limits the scope of direct exploration of scalar fields Isocontour extraction is a popular method for exploring scalar fields because of its simplicity in presenting features in the data In this paper, we present a novel representation of contours with the aim of studying the similarity relationship between the contours The representation maps contours to points in a high-dimensional transformation-invariant descriptor space We leverage the power of this representation to design a clustering based algorithm for detecting symmetric regions in a scalar field Symmetry detection is a challenging problem because it demands both segmentation of the data and identification of transformation invariant segments While the former task can be addressed using topological analysis of scalar fields, the latter requires geometry based solutions Our approach combines the two by utilizing the contour tree for segmenting the data and the descriptor space for determining transformation invariance We discuss two applications, query driven exploration and asymmetry visualization, that demonstrate the effectiveness of the approach

Multiscale Symmetry Detection in Scalar Fields by Clustering Contours.

Study of symmetric or repeating patterns in scalar fields is important in scientific data analysis because it gives deep insights into the properties of the underlying phenomenon. Though geometric symmetry has been well studied within areas like shape processing, identifying symmetry in scalar fields has remained largely unexplored due to the high computational cost of the associated algorithms. We propose a computationally efficient algorithm for detecting symmetric patterns in a scalar field distribution by analysing the topology of level sets of the scalar field. Our algorithm computes the contour tree of a given scalar field and identifies subtrees that are similar. We define a robust similarity measure for comparing subtrees of the contour tree and use it to group similar subtrees together. Regions of the domain corresponding to subtrees that belong to a common group are extracted and reported to be symmetric. Identifying symmetry in scalar fields finds applications in visualization, data exploration, and feature detection. We describe two applications in detail: symmetry-aware transfer function design and symmetry-aware isosurface extraction.

/pdf/symmetry-in-scalar-field-topology-1dy8tsw87y.pdf

Symmetry in Scalar Field Topology

Visualizing symmetric patterns in the data often helps the domain scientists make important observations and gain insights about the underlying experiment. Detecting symmetry in scalar fields is a nascent area of research and existing methods that detect symmetry are either not robust in the presence of noise or computationally costly. We propose a data structure called the augmented extremum graph and use it to design a novel symmetry detection method based on robust estimation of distances. The augmented extremum graph captures both topological and geometric information of the scalar field and enables robust and computationally efficient detection of symmetry. We apply the proposed method to detect symmetries in cryo-electron microscopy datasets and the experiments demonstrate that the algorithm is capable of detecting symmetry even in the presence of significant noise. We describe novel applications that use the detected symmetry to enhance visualization of scalar field data and facilitate their exploration.

Dilip Mathew Thomas

Papers

An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos

An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos

Multiscale Symmetry Detection in Scalar Fields by Clustering Contours.

Symmetry in Scalar Field Topology

Detecting Symmetry in Scalar Fields Using Augmented Extremum Graphs