Explainable Deep One-Class Classification

Cluster Computing

Deep learning-based video anomaly detection methods have drawn significant attention in the past few years due to their superior performance. However, almost all the leading methods for video anomaly detection rely on large-scale training datasets with long training times. As a result, many real-world video analysis tasks are still not applicable for fast deployment. On the other hand, the leading methods cannot provide interpretability due to the uninterpretable feature representations hiding the decision-making process when anomaly detection models are considered as a black box. However, the interpretability for anomaly detection is crucial since the corresponding response to the anomalies in the video is determined by their severity and nature. To tackle these problems, this paper proposes an efficient deep learning framework for video anomaly detection and provides explanations. The proposed framework uses pre-trained deep models to extract high-level concept and context features for training denoising autoencoder (DAE), requiring little training time (i.e., within 10 s on UCSD Pedestrian datasets) while achieving comparable detection performance to the leading methods. Furthermore, this framework presents the first video anomaly detection use of combing autoencoder and SHapley Additive exPlanations (SHAP) for model interpretability. The framework can explain each anomaly detection result in surveillance videos. In the experiments, we evaluate the proposed framework's effectiveness and efficiency while also explaining anomalies behind the autoencoder's prediction. On the USCD Pedestrian datasets, the DAE achieved 85.9% AUC with a training time of 5 s on the USCD Ped1 and 92.4% AUC with a training time of 2.9 s on the UCSD Ped2. Keywords Security Á Video surveillance Á Anomaly video analysis Á Abnormal event detection Á Deep features Á Context mining Á Interpretability

IEEE Access, 2021

Despite the superior performance in modeling complex patterns to address challenging problems, the black-box nature of Deep Learning (DL) methods impose limitations to their application in real-world critical domains. The lack of a smooth manner for enabling human reasoning about the black-box decisions hinder any preventive action to unexpected events, in which may lead to catastrophic consequences. To tackle the unclearness from black-box models, interpretability became a fundamental requirement in DL-based systems, leveraging trust and knowledge by providing ways to understand the model's behavior. Although a current hot topic, further advances are still needed to overcome the existing limitations of the current interpretability methods in unsupervised DL-based models for Anomaly Detection (AD). Autoencoders (AE) are the core of unsupervised DL-based for AD applications, achieving bestin-class performance. However, due to their hybrid aspect to obtain the results (by requiring additional calculations out of network), only agnostic interpretable methods can be applied to AE-based AD. These agnostic methods are computationally expensive to process a large number of parameters. In this paper, we present the RXP (Residual eXPlainer), a new interpretability method to deal with the limitations for AE-based AD in large-scale systems. It stands out for its implementation simplicity, low computational cost and deterministic behavior, in which explanations are obtained through the deviation analysis of reconstructed input features. In an experiment using data from a real heavy-haul railway line, the proposed method achieved superior performance compared to SHAP, demonstrating its potential to support decision making in large scale critical systems.

2022

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the task of unsupervised anomaly detection. We argue that explainability is principally an algorithmic task and interpretability is principally a cognitive task, and draw on insights from the cognitive sciences to propose a general-purpose method for practical diagnosis using explained anomalies. We define Attribution Error, and demonstrate, using real-world labeled datasets, that our method based on Integrated Gradients (IG) yields significantly lower attribution errors than alternative methods.

ArXiv, 2021

Detecting latent structure within a dataset is a crucial step in performing analysis of a dataset. However, existing state-ofthe-art techniques for subclass discovery are limited: either they are limited to detecting very small numbers of outliers or they lack the statistical power to deal with complex data such as image or audio. This paper proposes a solution to this subclass discovery problem: by leveraging instance explanation methods, an existing classifier can be extended to detect latent classes via differences in the classifier’s internal decisions about each instance. This works not only with simple classification techniques but also with deep neural networks, allowing for a powerful and flexible approach to detecting latent structure within datasets. Effectively, this represents a projection of the dataset into the classifier’s “explanation space,” and preliminary results show that this technique outperforms the baseline for the detection of latent classes even with limite...

2018

Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection. Those approaches which do exist involve networks trained to perform a task other than anomaly detection, namely generative models or compression, which are in turn adapted for use in anomaly detection; they are not trained on an anomaly detection based objective. In this paper we introduce a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective. The adaptation to the deep regime necessitates that our neural network and training procedure satisfy certain properties, which we demonstrate theoretically. We show the effectiveness of our method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GTSRB stop signs.

Data Mining and Knowledge Discovery

The accuracy and flexibility of Deep Convolutional Neural Networks (DCNNs) have been highly validated over the past years. However, their intrinsic opaqueness is still affecting their reliability and limiting their application in critical production systems, where the black-box behavior is difficult to be accepted. This work proposes EBAnO, an innovative explanation framework able to analyze the decision-making process of DCNNs in image classification by providing prediction-local and class-based model-wise explanations through the unsupervised mining of knowledge contained in multiple convolutional layers. EBAnO provides detailed visual and numerical explanations thanks to two specific indexes that measure the features’ influence and their influence precision in the decision-making process. The framework has been experimentally evaluated, both quantitatively and qualitatively, by (i) analyzing its explanations with four state-of-the-art DCNN architectures, (ii) comparing its result...

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021

Our objective is to detect anomalies in video while also automatically explaining the reason behind the detector's response. In a practical sense, explainability is crucial for this task as the required response to an anomaly depends on its nature and severity. However, most leading methods (based on deep neural networks) are not interpretable and hide the decision making process in uninterpretable feature representations. In an effort to tackle this problem we make the following contributions: (1) we show how to build interpretable feature representations suitable for detecting anomalies with state of the art performance, (2) we propose an interpretable probabilistic anomaly detector which can describe the reason behind it's response using high level concepts, (3) we are the first to directly consider object interactions for anomaly detection and (4) we propose a new task of explaining anomalies and release a large dataset for evaluating methods on this task. Our method competes well with the state of the art on public datasets while also providing anomaly explanation based on objects and their interactions.

2021

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...

2020

Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that sufficiently characterizes what it means to be "anomalous." In this paper we present results demonstrating that this intuition surprisingly does not extend to deep AD on images. For a recent AD benchmark on ImageNet, classifiers trained to discern between normal samples and just a few (64) random natural images are able to outperform the current state of the art in deep AD. We find that this approach is also very effective at other common image AD benchmarks. Experimentally we discover that the multiscale structure of image data makes example anomalies exceptionally informative.

2021

Detection of anomalies (i.e., outliers) in multi-dimensional data is a well-studied subject in machine learning. Unfortunately, unsupervised detectors provide no explanation about why a data point was considered as abnormal or which of its features (i.e. subspaces) exhibit at best its outlyingness. Such outlier explanations are crucial to diagnose the root cause of data anomalies and enable corrective actions to prevent or remedy their effect in downstream data processing. In this work, we present a comprehensive framework for comparing different unsupervised outlier explanation algorithms that are domain and detector-agnostic. Using real and synthetic datasets, we assess the effectiveness and efficiency of two point explanation algorithms (Beam [28] and RefOut [18]) ranking subspaces that best explain the outlyingness of individual data points and two explanation summarization algorithms (LookOut [15] and HiCS [17]) ranking subspaces that best exhibit as many outlier points from in...