International audienceExploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question. Previous works argued that training VAE models only with inliers is insufficient and the framework should be significantly modified in order to discriminate the anomalous instances. In this work, we exploit the deep conditional variational autoencoder (CVAE) and we define an original loss function together with a metric that targets hierarchically structured data AD. Our motivating application is a real world problem: monitoring the trigger system which is a basic component of many particle physics experiments at the CERN Large...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Anomaly detection and localization can learn what data looks like and point out anomalous data sampl...
Abstract Discoveries of new phenomena often involve a dedicate...
International audienceExploiting the rapid advances in probabilistic inference, in particular variat...
International audienceExploiting the rapid advances in probabilistic inference, in particular variat...
Anomaly Detection (AD) is an important research topic, with very diverse applications such as indust...
We investigate how to improve new physics detection strategies exploiting variational autoencoders a...
We investigate how to improve new physics detection strategies exploiting variational autoencoders a...
Abstract Using variational autoencoders trained on known physics processes, we develop a one-sided t...
Using variational autoencoders trained on known physics processes, we develop a one-sided threshold ...
We study the possibility of applying deep learning algorithms, suchas Variational Autoencoders, on s...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Anomaly detection and localization can learn what data looks like and point out anomalous data sampl...
Abstract Discoveries of new phenomena often involve a dedicate...
International audienceExploiting the rapid advances in probabilistic inference, in particular variat...
International audienceExploiting the rapid advances in probabilistic inference, in particular variat...
Anomaly Detection (AD) is an important research topic, with very diverse applications such as indust...
We investigate how to improve new physics detection strategies exploiting variational autoencoders a...
We investigate how to improve new physics detection strategies exploiting variational autoencoders a...
Abstract Using variational autoencoders trained on known physics processes, we develop a one-sided t...
Using variational autoencoders trained on known physics processes, we develop a one-sided threshold ...
We study the possibility of applying deep learning algorithms, suchas Variational Autoencoders, on s...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Anomaly detection and localization can learn what data looks like and point out anomalous data sampl...
Abstract Discoveries of new phenomena often involve a dedicate...