Related papers: Label Augmentation via Time-based Knowledge Distil…

Time series anomaly detection is a challenging problem due to the complex temporal dependencies and the limited label data. Although some algorithms including both traditional and deep models have been proposed, most of them mainly focus on…

The rise of digital ecosystems has exposed the financial sector to evolving abuse and criminal tactics that share operational knowledge and techniques both within and across different environments (fiat-based, crypto-assets, etc.).…

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image…

Most previous methods for text data augmentation are limited to simple tasks and weak baselines. We explore data augmentation on hard tasks (i.e., few-shot natural language understanding) and strong baselines (i.e., pretrained models with…

In recent years, the unprecedented growth in digital payments fueled consequential changes in fraud and financial crimes. In this new landscape, traditional fraud detection approaches such as rule-based engines have largely become…

Canine cardiomegaly, marked by an enlarged heart, poses serious health risks if undetected, requiring accurate diagnostic methods. Current detection models often rely on small, poorly annotated datasets and struggle to generalize across…

Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks. Recently, researchers proposed a few intensive data augmentation techniques, which indeed…

The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…

Deep convolutional neural networks have achieved exceptional results on multiple detection and recognition tasks. However, the performance of such detectors are often evaluated in public benchmarks under constrained and non-realistic…

Anomaly detection, a critical facet in data analysis, involves identifying patterns that deviate from expected behavior. This research addresses the complexities inherent in anomaly detection, exploring challenges and adapting to…

Detecting anomalies in data is a vital task, with numerous high-impact applications in areas such as security, finance, health care, and law enforcement. While numerous techniques have been developed in past years for spotting outliers and…

As the availability of financial services online continues to grow, the incidence of fraud has surged correspondingly. Fraudsters continually seek new and innovative ways to circumvent the detection algorithms in place. Traditionally, fraud…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Exploring adversarial attack vectors and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image…

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most…

Time-series anomaly detection plays an important role in engineering processes, like development, manufacturing and other operations involving dynamic systems. These processes can greatly benefit from advances in the field, as…

Detecting anomalies in a temporal sequence of graphs can be applied is areas such as the detection of accidents in transport networks and cyber attacks in computer networks. Existing methods for detecting abnormal graphs can suffer from…

Medical research, particularly in predicting patient outcomes, heavily relies on medical time series data extracted from Electronic Health Records (EHR), which provide extensive information on patient histories. Despite rigorous…

Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and…

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection…