Image anomaly detection is to distinguish a small portion of images that are different from the user-defined normal ones. In this work, we focus on auto-encoders based anomaly detection models, which assess the probability of anomaly by measuring reconstruction errors. One of the critical steps in image anomaly detection is to extract robust and distinguishable representations that could separate abnormal patterns from normal ones. However, current auto-encoder based methods fail to extract such distinguishable representations because their optimization objectives are not tailored for this specific task. Besides, the architectures of those models are unable to capture features that are robust to irrelevant distortions but sensitive to abnor...
Image anomaly detection consists in detecting images or image portions that are visually different f...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Recent advances in deep learning led to novel generative modeling techniques that achieve unpreceden...
Visual anomaly detection, the task of isolating visual data that do not conform to the defined notio...
Anomaly Detection (AD) is to identify samples that differ from training observations in some way. Th...
Deep autoencoders provide an effective tool for learning non-linear dimensionality reduction in an u...
We propose a method for video anomaly detection using a winner-take-all convolutional autoencoder th...
Anomaly detection refers to the task of finding unusual instancesthat stand out from the normal data...
This thesis concerns deep learning approaches for anomaly detection in images. Anomaly detection add...
Anomaly detection is an important problem that has been well-studied within diverse research areas a...
International audienceDeep anomaly detection has recently seen significantdevelopments to provide ro...
International audienceDeep anomaly detection has recently seen significantdevelopments to provide ro...
The capability of deep learning (DL) techniques for dealing with non-linear, dynamic and correlated ...
This thesis is a collection of three engineering-based research contributions, aiming to detect anom...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Image anomaly detection consists in detecting images or image portions that are visually different f...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Recent advances in deep learning led to novel generative modeling techniques that achieve unpreceden...
Visual anomaly detection, the task of isolating visual data that do not conform to the defined notio...
Anomaly Detection (AD) is to identify samples that differ from training observations in some way. Th...
Deep autoencoders provide an effective tool for learning non-linear dimensionality reduction in an u...
We propose a method for video anomaly detection using a winner-take-all convolutional autoencoder th...
Anomaly detection refers to the task of finding unusual instancesthat stand out from the normal data...
This thesis concerns deep learning approaches for anomaly detection in images. Anomaly detection add...
Anomaly detection is an important problem that has been well-studied within diverse research areas a...
International audienceDeep anomaly detection has recently seen significantdevelopments to provide ro...
International audienceDeep anomaly detection has recently seen significantdevelopments to provide ro...
The capability of deep learning (DL) techniques for dealing with non-linear, dynamic and correlated ...
This thesis is a collection of three engineering-based research contributions, aiming to detect anom...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Image anomaly detection consists in detecting images or image portions that are visually different f...
We propose an out-of-distribution detection method that combines density and restoration-based appro...
Recent advances in deep learning led to novel generative modeling techniques that achieve unpreceden...