3 papers
cs.CV2022
ScaleFace: Uncertainty-aware Deep Metric Learning
Roman Kail, Kirill Fedyanin, Nikita Muravev +2
The performance of modern deep learning-based systems dramatically depends on the quality of input objects. For example, face recognition quality would be lower for blurry or corru…
stat.ML2022
Embedded Ensembles: Infinite Width Limit and Operating Regimes
Maksim Velikanov, Roman Kail, Ivan Anokhin +4
A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as E…
cs.LG2020
Recurrent Convolutional Neural Networks help to predict location of Earthquakes
Roman Kail, Alexey Zaytsev, Evgeny Burnaev
We examine the applicability of modern neural network architectures to the midterm prediction of earthquakes. Our data-based classification model aims to predict if an earthquake w…