Deep Learning performs well when training data densely covers the experience space. For complex problems this makes data collection prohibitively expensive. We propose to intelligently select samples when constructing data sets in order to best utilize the available labeling budget. The selection methodology is based on the presumption that two dissimilar samples are worth more than two similar samples in a data set. Similarity is measured based on the Euclidean distance between samples in the latent space produced by a DNN. By using a self-supervised method to construct the latent space, it is ensured that the space fits the data well and that any upfront labeling effort can be avoided. The result is more efficient, diverse, and balanced data set, which produce equal or superior results with fewer labeled examples.
One-class novelty detectors are trained with examples of a particular class and are tasked with identifying whether a query example belongs to the same known class. Most recent advances adopt a deep auto-encoder style architecture to compute novelty scores for detecting novel class data. Deep networks have shown to be vulnerable to adversarial attacks, yet little focus is devoted to studying the adversarial robustness of deep novelty detectors. In this paper, we first show that existing novelty detectors are susceptible to adversarial examples. We further demonstrate that commonly-used defense…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex due to the unpredictable nature of novelties and its inaccessibility during the training procedure, factors which expose the unsupervised nature of the problem. In our proposal, we design a general framework where we equip a deep autoencoder with a parametric density estimator that learns the probability distribution underlying its latent representations thr…
Point Cloud Novelty Detection Based on Latent Representations of a General Feature Extractor
Graduate School of Science and Technology, University of Tsukuba（科技研究生学校，茨口大学）；Institute of Systems and Information Engineering, University of Tsukuba（系统与信息工程研究所，茨口大学）；Center for Artificial Intelligence Research, University of Tsukuba（人工智能研究中心，茨口大学）；Division of Physics, Faculty of Pure and Applied Sciences, University of Tsukuba（物理系，应用科学 faculty，茨口大学）；Tomonaga Center for the History of the Universe (TCHoU), Faculty of Pure and Applied Sciences, University of Tsukuba（汤本纳宇宙历史中心（TCHoU），应用科学 faculty，茨口大学）
Seoul National University（首尔国立大学）；University of California, Davis（加州大学戴维斯分校）
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of different features other than class information which makes models hard to detect novelty data. The problem gets harder in multi-modal normality case. To address this challenge, we propose a new way of measuring novelty score in multi-modal normality cases using orthogonalized latent space. Specifically, we employ orthogonal low-rank embedding in the latent space t…
We present a novel model called OCGAN for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if a query example is from the same class. Our solution is based on learning latent representations of in-class examples using a denoising auto-encoder network. The key contribution of our work is our proposal to explicitly constrain the latent space to exclusively represent the given class. In order to accomplish this goal, firstly, we force the latent space to have bounded support by introducing a tanh activation in t…
In one-class novelty detection, a model learns solely on the in-class data to single out out-class instances. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, thus differentiating the in-class from out-class by the reconstruction error. However, compact modeling in an improper way might collapse the latent representations of the in-class data and thus their reconstruction, which would lead to performance deterioration. Moreover, to properly measure the reconstruction error of high-dimensional data, a metric is required that captures high-level s…
CARISSMA, Technische Hochschule Ingolstadt（CARISSMA，因戈尔施塔特应用技术大学）；Technical University of Munich（慕尼黑工业大学）
Detecting unknown and untested scenarios is crucial for scenario-based testing. Scenario-based testing is considered to be a possible approach to validate autonomous vehicles. A traffic scenario consists of multiple components, with infrastructure being one of it. In this work, a method to detect novel traffic scenarios based on their infrastructure images is presented. An autoencoder triplet network provides latent representations for infrastructure images which are used for outlier detection. The triplet training of the network is based on the connectivity graphs of the infrastructure. By us…
East China Normal University（华东师范大学）；Tencent Youtu Lab（腾讯优图实验室）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang Lab（之江实验室）
Novelty detection is the process of determining whether a query example differs from the learned training distribution. Previous methods attempt to learn the representation of the normal samples via generative adversarial networks (GANs). However, they will suffer from instability training, mode dropping, and low discriminative ability. Recently, various pretext tasks (e.g. rotation prediction and clustering) have been proposed for self-supervised learning in novelty detection. However, the learned latent features are still low discriminative. We overcome such problems by introducing a novel d…
Emory University（埃默里大学）；Indiana University-Purdue University Indianapolis（印第安纳大学-普渡大学印第安纳波利斯分校）；Mayo Clinic（梅奥诊所）；Arizona State University（亚利桑那州立大学）
Traditional anomaly detection methods focus on detecting inter-class variations while medical image novelty identification is inherently an intra-class detection problem. For example, a machine learning model trained with normal chest X-ray and common lung abnormalities, is expected to discover and flag idiopathic pulmonary fibrosis which a rare lung disease and unseen by the model during training. The nuances from intra-class variations and lack of relevant training data in medical image analysis pose great challenges for existing anomaly detection methods. To tackle the challenges, we propos…
Zhejiang University of Technology（浙江工业大学）；Tianjin University of Technology（天津理工大学）
Novelty detection is a important research area which mainly solves the classification problem of inliers which usually consists of normal samples and outliers composed of abnormal samples. Auto-encoder is often used for novelty detection. However, the generalization ability of the auto-encoder may cause the undesirable reconstruction of abnormal elements and reduce the identification ability of the model. To solve the problem, we focus on the perspective of better reconstructing the normal samples as well as retaining the unique information of normal samples to improve the performance of auto-…
Novelty detection, a widely studied problem in machine learning, is the problem of detecting a novel class of data that has not been previously observed. A common setting for novelty detection is inductive whereby only examples of the negative class are available during training time. Transductive novelty detection on the other hand has only witnessed a recent surge in interest, it not only makes use of the negative class during training but also incorporates the (unlabeled) test set to detect novel examples. Several studies have emerged under the transductive setting umbrella that have demons…
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to a natural image. This property emerges from the disentangled nature of the latent space. In this paper, we identify two geometric limitations of such latent space: (a) euclidean distances differ from image perceptual distance, and (b) disentanglement is not optimal and facial attribute separation using linear model is a limiting hypothesis. We thus propose a new method to learn a proxy latent representation using normalizing flows to r…
Sapienza University of Rome（罗马第一大学）；Cardiff University（卡迪夫大学）；Technical University of Munich（慕尼黑工业大学）
In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders (VAEs) on normal data. Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regu…
In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance. Specifically, we perform one-to-one data augmentation to learn the more effective features. The data and the augmented data are simultaneous…
In anomaly detection (AD), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generative models, such as variational autoencoders (VAEs), for unsupervised learning of the normal data distribution. In semi-supervised AD (SSAD), the data also includes a small sample of labeled anomalies. In this work, we propose two variational methods for training VAEs for SSAD. The intuitive idea in both methods is to train the encoder to `separate' between latent vectors for normal and outlier data. We show that thi…
Binary classification (BC) is a practical task that is ubiquitous in real-world problems, such as distinguishing healthy and unhealthy objects in biomedical diagnostics and defective and non-defective products in manufacturing inspections. Nonetheless, fully annotated data are commonly required to effectively solve this problem, and their collection by domain experts is a tedious and expensive procedure. In contrast to BC, several significant semi-supervised learning techniques that heavily rely on stochastic data augmentation techniques have been devised for solving multi-class classification…
Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Georgia Tech Europe（佐治亚理工学院欧洲校区）；Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人学与控制论研究所）；Czech Technical University in Prague（布拉格捷克理工大学）
Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. However, the number of constraints is quadratic or even cubic in the number of the original examples, which makes it challenging for DML to handle the large-scale data set. Besides, the real-world data may contain various uncertainty, especially for the image data. The uncertainty can mislead the learning procedure and cause the performance degradation. B…
Institut de Recherche en Informatique de Toulouse（图卢兹计算机科学研究所）；Université de Toulouse（图卢兹大学）；Solution Data Group, IA department（Solution Data Group（人工智能部门））；École nationale supérieure des mines d’Alès（阿尔勒国立高等矿业学校）；Toulouse（图卢兹）
This paper addresses the problem of vehicle re-identification using distance comparison of images in CNN latent spaces. Firstly, we study the impact of the distance metrics, comparing performances obtained with different metrics: the minimal Euclidean distance (MED), the minimal cosine distance (MCD), and the residue of the sparse coding reconstruction (RSCR). These metrics are applied using features extracted from five different CNN architectures, namely ResNet18, AlexNet, VGG16, InceptionV3 and DenseNet201. We use the specific vehicle re-identification dataset VeRi to fine-tune these CNNs an…
Generative models dealing with modeling a~joint data distribution are generally either autoencoder or GAN based. Both have their pros and cons, generating blurry images or being unstable in training or prone to mode collapse phenomenon, respectively. The objective of this paper is to construct a~model situated between above architectures, one that does not inherit their main weaknesses. The proposed LCW generator (Latent Cramer-Wold generator) resembles a classical GAN in transforming Gaussian noise into data space. What is of utmost importance, instead of a~discriminator, LCW generator uses k…
In the field of pattern classification, the training of deep learning classifiers is mostly end-to-end learning, and the loss function is the constraint on the final output (posterior probability) of the network, so the existence of Softmax is essential. In the case of end-to-end learning, there is usually no effective loss function that completely relies on the features of the middle layer to restrict learning, resulting in the distribution of sample latent features is not optimal, so there is still room for improvement in classification accuracy. Based on the concept of Predefined Evenly-Dis…
