Related papers: Connective Reconstruction-based Novelty Detection

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.…

Despite the success of Generative Adversarial Networks (GANs), mode collapse remains a serious issue during GAN training. To date, little work has focused on understanding and quantifying which modes have been dropped by a model. In this…

We consider the following problem: we have a large dataset of normal data available. We are now given a new, possibly quite small, set of data, and we are to decide if these are normal data, or if they are indicating a new phenomenon. This…

Anomaly detection in medical images is challenging due to limited annotations and a domain gap compared to natural images. Existing reconstruction methods often rely on frozen pre-trained encoders, which limits adaptation to domain-specific…

Novelty detection seeks to identify samples deviating from a known distribution, yet data shifts in a multitude of ways, and only a few consist of relevant changes. Aligned with out-of-distribution generalization literature, we advocate for…

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise. The ability to synthesize high-quality content at a large scale brings potential risks…

Inverse problems arise in a multitude of applications, where the goal is to recover a clean signal from noisy and possibly (non)linear observations. The difficulty of a reconstruction problem depends on multiple factors, such as the ground…

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection…

A critical vulnerability of supervised deep learning in high-dimensional tabular domains is "generalization collapse": models form precise decision boundaries around known training distributions but fail catastrophically when encountering…

In real-world applications, input data distributions are rarely static over a period of time, a phenomenon known as concept drift. Such concept drifts degrade the model's prediction performance, and therefore we require methods to overcome…

This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN). Modeling probability distributions on deep features has recently emerged as an effective, yet computationally cheap…

An approach to utilize recent advances in deep generative models for anomaly detection in a granular (continuous) sense on a real-world image dataset with quality issues is detailed using recent normalizing flow models, with implications in…

Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area…

Supervised classification methods have been widely utilized for the quality assurance of the advanced manufacturing process, such as additive manufacturing (AM) for anomaly (defects) detection. However, since abnormal states (with defects)…

Convolutional neural networks (CNNs) learn abstract features to perform object classification, but understanding these features remains challenging due to difficult-to-interpret results or high computational costs. We propose an automatic…

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the…

Generative models, such as GANs, learn an explicit low-dimensional representation of a particular class of images, and so they may be used as natural image priors for solving inverse problems such as image restoration and compressive…

We propose introspective convolutional networks (ICN) that emphasize the importance of having convolutional neural networks empowered with generative capabilities. We employ a reclassification-by-synthesis algorithm to perform training…

Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder with no notion of uncertainty or confidence. In this paper, we…