Related papers: Neural Transformation Learning for Deep Anomaly De…

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the…

A dramatic rise in the flow of manipulated image content on the Internet has led to an aggressive response from the media forensics research community. New efforts have incorporated increased usage of techniques from computer vision and…

In the research area of anomaly detection, novel and promising methods are frequently developed. However, most existing studies exclusively focus on the detection task only and ignore the interpretability of the underlying models as well as…

Direct image-to-graph transformation is a challenging task that involves solving object detection and relationship prediction in a single model. Due to this task's complexity, large training datasets are rare in many domains, making the…

Unsupervised anomaly detection aims to build models to effectively detect unseen anomalies by only training on the normal data. Although previous reconstruction-based methods have made fruitful progress, their generalization ability is…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

Deep neural networks are highly effective in solving complex problems but are often viewed as "black boxes," limiting their adoption in contexts where transparency and explainability are essential. This lack of visibility raises ethical and…

Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI. The main principle behind these works is to learn a model of normal anatomy by learning to…

Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with unstructured data, their efficacy with structured data has…

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

Anomaly detection in surveillance videos has been recently gaining attention. Even though the performance of state-of-the-art methods on publicly available data sets has been competitive, they demand a massive amount of training data. Also,…

In this work, we propose several enhancements to a geometric transformation based model for anomaly detection in images (GeoTranform). The model assumes that the anomaly class is unknown and that only inlier samples are available for…

Detecting anomalies in musculoskeletal radiographs is of paramount importance for large-scale screening in the radiology workflow. Supervised deep networks take for granted a large number of annotations by radiologists, which is often…

One-class anomaly detection is challenging. A representation that clearly distinguishes anomalies from normal data is ideal, but arriving at this representation is difficult since only normal data is available at training time. We examine…

Light scattering and aberrations limit optical microscopy in biological tissue, which motivates the development of adaptive optics techniques. Here, we develop a method for adaptive optics with reflected light and deep neural networks…

Inverse problems arise in a variety of imaging applications including computed tomography, non-destructive testing, and remote sensing. The characteristic features of inverse problems are the non-uniqueness and instability of their…

The recent rapid development of deep learning has laid a milestone in industrial Image Anomaly Detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the…

Recent advances in deep learning-based medical image registration have shown that training deep neural networks~(DNNs) does not necessarily require medical images. Previous work showed that DNNs trained on randomly generated images with…

Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for…

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color…