ScaleFace: Uncertainty-aware Deep Metric Learning

1 code implementation • 5 Sep 2022 • Roman Kail, Kirill Fedyanin, Nikita Muravev, Alexey Zaytsev, Maxim Panov

The performance of modern deep learning-based systems dramatically depends on the quality of input objects.

Face Recognition Image Retrieval +2

Embedded Ensembles: Infinite Width Limit and Operating Regimes

no code implementations • 24 Feb 2022 • Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky

In this limit, we identify two ensemble regimes - independent and collective - depending on the architecture and initialization strategy of ensemble models.

Recurrent Convolutional Neural Networks help to predict location of Earthquakes

1 code implementation • 20 Apr 2020 • Roman Kail, Alexey Zaytsev, Evgeny Burnaev

For historical data on Japan earthquakes our model predicts occurrence of an earthquake in $10$ to $60$ days from a given moment with magnitude $M_c > 5$ with quality metrics ROC AUC $0. 975$ and PR AUC $0. 0890$, making $1. 18 \cdot 10^3$ correct predictions, while missing $2. 09 \cdot 10^3$ earthquakes and making $192 \cdot 10^3$ false alarms.