no code implementations • 10 Jun 2023 • Maria Dziuba, Ivan Jarsky, Valeria Efimova, Andrey Filchenkov
Vectorization is the process of converting a raster image into a similar vector image using primitive shapes.
1 code implementation • 6 Mar 2023 • Valeria Efimova, Artyom Chebykin, Ivan Jarsky, Evgenii Prosvirnin, Andrey Filchenkov
We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image.
no code implementations • 18 Jul 2022 • Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov
Adversarial examples are transferable between different models.
no code implementations • 18 Jul 2022 • Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov
It was shown that adversarial examples improve object recognition.
no code implementations • 30 May 2022 • Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov, Andrey Filchenkov
In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain.
1 code implementation • 15 May 2022 • Valeria Efimova, Ivan Jarsky, Ilya Bizyaev, Andrey Filchenkov
As almost all the existing image synthesis algorithms consider an image as a pixel matrix, the high-resolution image synthesis is complicated. A good alternative can be vector images.
no code implementations • 29 Sep 2021 • Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov, Andrey Filchenkov
In our algorithm, instead of mapping from target to the source domain, optimal transport maps target samples to the set of adversarial examples.
no code implementations • 2 Aug 2021 • Natalia Khanzhina, Alexey Lapenok, Andrey Filchenkov
According to recent studies, commonly used computer vision datasets contain about 4% of label errors.
no code implementations • 20 Jun 2021 • Qi Yang, Aleksandr Farseev, Andrey Filchenkov
We have also found that the selection of a machine learning approach is of crucial importance when choosing social network data sources and that people tend to reveal multiple facets of their personality in different social media avenues.
1 code implementation • 16 Jun 2021 • Igor Kuznetsov, Andrey Filchenkov
The application of episodic memory for continuous control with a large action space is not trivial.
no code implementations • 30 Nov 2020 • Aleksandr Farseev, Qi Yang, Andrey Filchenkov, Kirill Lepikhin, Yu-Yi Chu-Farseeva, Daron-Benjamin Loo
Guided by the MBTI personality type, automatically derived from a user social network content, SoMin. ai generates new social media content based on the preferences of other users with a similar personality type aiming at enhancing the user experience on social networking venues as well diversifying the efforts of marketers when crafting new content for digital marketing campaigns.
no code implementations • 23 Oct 2020 • Gideon Stein, Andrey Filchenkov, Arip Asadulaev
To support the findings of this work, this paper seeks to provide an additional example of a Transformer-based RL method.
no code implementations • 5 Feb 2020 • Qi Yang, Aleksandr Farseev, Andrey Filchenkov
Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks.
no code implementations • 13 Jun 2019 • Arip Asadulaev, Igor Kuznetsov, Gideon Stein, Andrey Filchenkov
In this paper, we try to answer the following question: Can information about policy conditioning help to shape a more stable and general policy of reinforcement learning agents?
no code implementations • 13 Jun 2019 • Arip Asadulaev, Igor Kuznetsov, Andrey Filchenkov
It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions.
1 code implementation • 29 May 2017 • Evgeny Zamyatin, Andrey Filchenkov
In particular, it does not allow to train convolutional GAN models with fully-connected hidden layers.
no code implementations • WS 2017 • Kseniya Buraya, Lidia Pivovarova, Sergey Budkov, Andrey Filchenkov
This work deals with ontology learning from unstructured Russian text.
no code implementations • 7 Nov 2016 • Ivan Smetannikov, Ilya Isaev, Andrey Filchenkov
One of the classical problems in machine learning and data mining is feature selection.
no code implementations • 7 Nov 2016 • Valeria Efimova, Andrey Filchenkov, Anatoly Shalyto
In this paper, we present a new method for the simultaneous selection of an algorithm and its hyperparameters.