Related papers: Continual-MEGA: A Large-scale Benchmark for Genera…

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual…

In anomaly detection, a prominent task is to induce a model to identify anomalies learned solely based on normal data. Generally, one is interested in finding an anomaly detector that correctly identifies anomalies, i.e., data points that…

Detection of anomalous situations for complex mission-critical systems hold paramount importance when their service continuity needs to be ensured. A major challenge in detecting anomalies from the operational data arises due to the…

Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare. While VAD has been extensively studied, two key challenges remain largely unaddressed in conjunction: edge deployment,…

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while…

Anomaly detection is to recognize samples that differ in some respect from the training observations. These samples which do not conform to the distribution of normal data are called outliers or anomalies. In real-world anomaly detection…

Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of…

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization…

The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide…

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…

Anomaly detection suffered from the lack of anomalies due to the diversity of abnormalities and the difficulties of obtaining large-scale anomaly data. Semi-supervised anomaly detection methods are often used to solely leverage normal data…

Anomaly detection in large datasets is essential in astronomy and computer vision. However, due to a scarcity of labelled data, it is often infeasible to apply supervised methods to anomaly detection. We present AnomalyMatch, an anomaly…

Deep anomaly detection (AD) aims to provide robust and efficient classifiers for one-class and unbalanced settings. However current AD models still struggle on edge-case normal samples and are often unable to keep high performance over…

Recent advancements in large-scale visual-language pre-trained models have led to significant progress in zero-/few-shot anomaly detection within natural image domains. However, the substantial domain divergence between natural and medical…

With increased reliance on Internet based technologies, cyberattacks compromising users' sensitive data are becoming more prevalent. The scale and frequency of these attacks are escalating rapidly, affecting systems and devices connected to…

Unsupervised Continuous Anomaly Detection (UCAD) is gaining attention for effectively addressing the catastrophic forgetting and heavy computational burden issues in traditional Unsupervised Anomaly Detection (UAD). However, existing UCAD…

Anomaly detection in complex domains poses significant challenges due to the need for extensive labeled data and the inherently imbalanced nature of anomalous versus benign samples. Graph-based machine learning models have emerged as a…

Machine learning offers potential solutions to current issues in industrial systems in areas such as quality control and predictive maintenance, but also faces unique barriers in industrial applications. An ongoing challenge is extreme…