no code implementations • 16 Jan 2023 • Kostiantyn Khabarlak
The final trained model can be switched at runtime between 6 PTA configurations, which differ by inference time and quality.
no code implementations • 27 Jul 2022 • Kostiantyn Khabarlak
However, a single model might not give the best results for different device performance categories, while training multiple models is time consuming.
no code implementations • 13 Jun 2022 • Kostiantyn Khabarlak
In certain cases, quality improvement is possible by a careful pattern selection.
no code implementations • 11 May 2022 • Kostiantyn Khabarlak
In many practical cases face detection on smartphones or other highly portable devices is a necessity.
1 code implementation • 25 Oct 2021 • Andrei Boiarov, Kostiantyn Khabarlak, Igor Yastrebov
We propose and investigate the use of methods from the family of Simultaneous Perturbation Stochastic Approximation (SPSA) for optimization of meta-train tasks weights.
no code implementations • 11 Mar 2021 • Kostiantyn Khabarlak, Larysa Koriashkina
Also, we propose a mobile application that allows gate registration and serves as a door unlock key.
Cryptography and Security
no code implementations • 12 Jan 2021 • Kostiantyn Khabarlak, Larysa Koriashkina
Dense facial landmark detection is one of the key elements of face processing pipeline.
no code implementations • 23 Apr 2019 • Kostiantyn Khabarlak, Larysa Koriashkina
The presented adversarial attack analysis and the idea of attack scoping can be easily expanded to different datasets, thus making the paper's results applicable to a wide range of practical tasks.