Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Erlygin, Leonid"'
Autor:
Erlygin, Leonid, Zaytsev, Alexey
Accurately estimating image quality and model robustness improvement are critical challenges in unconstrained face recognition, which can be addressed through uncertainty estimation via probabilistic face embeddings. Previous research mainly focused
Externí odkaz:
http://arxiv.org/abs/2408.14229
Autor:
Erlygin, Leonid, Zholobov, Vladimir, Baklanova, Valeriia, Sokolovskiy, Evgeny, Zaytsev, Alexey
Machine learning models are widely used to solve real-world problems in science and industry. To build robust models, we should quantify the uncertainty of the model's predictions on new data. This study proposes a new method for uncertainty estimati
Externí odkaz:
http://arxiv.org/abs/2302.02834
Publikováno v:
IEEE Access. 2022 Apr 21;10:45256-65
As of today, the best accuracy in line segment detection (LSD) is achieved by algorithms based on convolutional neural networks - CNNs. Unfortunately, these methods utilize deep, heavy networks and are slower than traditional model-based detectors. I
Externí odkaz:
http://arxiv.org/abs/2209.04642