Related papers: A new interpretable unsupervised anomaly detection…

Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems that could compromise safety and lead to hazardous situations. Current approaches, which often rely on…

Reliable uncertainty estimation has become a crucial requirement for the industrial deployment of deep learning algorithms, particularly in high-risk applications such as autonomous driving and medical diagnosis. However, mainstream…

The aim of this paper is to formalise the task of continual semi-supervised anomaly detection (CSAD), with the aim of highlighting the importance of such a problem formulation which assumes as close to real-world conditions as possible.…

Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while…

This paper addresses trust issues created from the ubiquity of black box algorithms and surrogate explainers in Explainable Intrusion Detection Systems (X-IDS). While Explainable Artificial Intelligence (XAI) aims to enhance transparency,…

Anomaly detection (AD) plays a vital role across a wide range of domains, but its performance might deteriorate when applied to target domains with limited data. Domain Adaptation (DA) offers a solution by transferring knowledge from a…

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle…

Explainable artificial intelligence (xAI) has gained significant attention in recent years. Among other things, explainablility for deep neural networks has been a topic of intensive research due to the meteoric rise in prominence of deep…

For data-constrained, complex and dynamic industrial environments, there is a critical need for transferable and multimodal methodologies to enhance anomaly detection and therefore, prevent costs associated with system failures. Typically,…

Introduction: Machine learning provides fundamental tools both for scientific research and for the development of technologies with significant impact on society. It provides methods that facilitate the discovery of regularities in data and…

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…

Artificial intelligence (AI) is being applied in almost every field. At the same time, the currently dominant deep learning methods are fundamentally black-box systems that lack explanations for their inferences, significantly limiting…

In recent years, considerable progress has been made on improving the interpretability of machine learning models. This is essential, as complex deep learning models with millions of parameters produce state of the art results, but it can…

Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this…

Dynamic graph anomaly detection (DGAD) is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies. Existing methods are either unsupervised or semi-supervised: unsupervised methods avoid…

Anomaly detection in industrial visual inspection is challenging due to the scarcity of defective samples. Most existing methods rely on unsupervised reconstruction using only normal data, often resulting in overfitting and poor detection…

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…