Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Thimonier, Hugo"'
Autor:
Thimonier, Hugo, Costa, José Lucas De Melo, Popineau, Fabrice, Rimmel, Arpad, Doan, Bich-Liên
Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples. Self-supervised learning (SSL) generally involves generating different views of the same sample and thus
Externí odkaz:
http://arxiv.org/abs/2410.05016
Deep learning for tabular data has garnered increasing attention in recent years, yet employing deep models for structured data remains challenging. While these models excel with unstructured data, their efficacy with structured data has been limited
Externí odkaz:
http://arxiv.org/abs/2401.17052
This study explores the application of anomaly detection (AD) methods in imbalanced learning tasks, focusing on fraud detection using real online credit card payment data. We assess the performance of several recent AD methods and compare their effec
Externí odkaz:
http://arxiv.org/abs/2312.13896
Anomaly detection is vital in many domains, such as finance, healthcare, and cybersecurity. In this paper, we propose a novel deep anomaly detection method for tabular data that leverages Non-Parametric Transformers (NPTs), a model initially proposed
Externí odkaz:
http://arxiv.org/abs/2305.15121
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN)
As with many other tasks, neural networks prove very effective for anomaly detection purposes. However, very few deep-learning models are suited for detecting anomalies on tabular datasets. This paper proposes a novel methodology to flag anomalies ba
Externí odkaz:
http://arxiv.org/abs/2205.01362
Publikováno v:
2021 IEEE International Conference on Multimedia and Expo (ICME)
When trying to independently apply image-trained algorithms to successive frames in videos, noxious flickering tends to appear. State-of-the-art post-processing techniques that aim at fostering temporal consistency, generate other temporal artifacts
Externí odkaz:
http://arxiv.org/abs/2103.07278