1 code implementation • ICML 2020 • Ivan Nazarov, Evgeny Burnaev
With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural representation in the complex domain.
no code implementations • 6 Feb 2024 • Alexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Evgeny Burnaev, Alexander Korotin
Given a collection of probability measures, a practitioner sometimes needs to find an "average" distribution which adequately aggregates reference distributions.
1 code implementation • 5 Feb 2024 • Nikita Gushchin, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin
It exploits the optimal parameterization of the diffusion process and provably recovers the SB process \textbf{(a)} with a single bridge matching step and \textbf{(b)} with arbitrary transport plan as the input.
1 code implementation • 29 Jan 2024 • Viktor Moskvoretskii, Dmitry Osin, Egor Shvetsov, Igor Udovichenko, Maxim Zhelnin, Andrey Dukhovny, Anna Zhimerikina, Albert Efimov, Evgeny Burnaev
This study investigates self-supervised learning techniques to obtain representations of Event Sequences.
1 code implementation • 6 Jan 2024 • Igor Udovichenko, Egor Shvetsov, Denis Divitsky, Dmitry Osin, Ilya Trofimov, Anatoly Glushenko, Ivan Sukharev, Dmitry Berestenev, Evgeny Burnaev
As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications.
no code implementations • 22 Dec 2023 • Sergei Shumilin, Alexander Ryabov, Evgeny Burnaev, Vladimir Vanovskii
We present the method for autodifferentiation of the 2D Voronoi tessellation.
no code implementations • 7 Dec 2023 • Savva Ignatyev, Daniil Selikhanovych, Oleg Voynov, Yiqun Wang, Peter Wonka, Stamatios Lefkimmiatis, Evgeny Burnaev
We present a novel method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured.
no code implementations • 30 Nov 2023 • Natalia Soboleva, Olga Gorbunova, Maria Ivanova, Evgeny Burnaev, Matthias Nießner, Denis Zorin, Alexey Artemov
We define and learn a collection of surface-based fields to (1) capture sharp geometric features in the shape with an implicit vertexwise model and (2) approximate improvements in normals alignment obtained by applying edge-flips with an edgewise model.
no code implementations • 18 Nov 2023 • Diana Koldasbayeva, Polina Tregubova, Mikhail Gasanov, Alexey Zaytsev, Anna Petrovskaia, Evgeny Burnaev
With the rise of electronic data, particularly Earth observation data, data-based geospatial modelling using machine learning (ML) has gained popularity in environmental research.
no code implementations • 2 Oct 2023 • Alexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin
Optimal transport (OT) barycenters are a mathematically grounded way of averaging probability distributions while capturing their geometric properties.
1 code implementation • 2 Oct 2023 • Alexander Korotin, Nikita Gushchin, Evgeny Burnaev
Despite the recent advances in the field of computational Schr\"odinger Bridges (SB), most existing SB solvers are still heavy-weighted and require complex optimization of several neural networks.
no code implementations • 24 Aug 2023 • Nikita Balabin, Daria Voronkova, Ilya Trofimov, Evgeny Burnaev, Serguei Barannikov
We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding multi-scale topological loss term.
1 code implementation • 27 Jun 2023 • Dmitrii Gavrilev, Evgeny Burnaev
Node outlier detection in attributed graphs is a challenging problem for which there is no method that would work well across different datasets.
1 code implementation • NeurIPS 2023 • Nikita Gushchin, Alexander Kolesov, Petr Mokrov, Polina Karpikova, Andrey Spiridonov, Evgeny Burnaev, Alexander Korotin
We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution is known by the construction.
1 code implementation • NeurIPS 2023 • Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey Nikolenko, Evgeny Burnaev
Rapidly increasing quality of AI-generated content makes it difficult to distinguish between human and AI-generated texts, which may lead to undesirable consequences for society.
no code implementations • 29 May 2023 • Yue Fan, Ivan Skorokhodov, Oleg Voynov, Savva Ignatyev, Evgeny Burnaev, Peter Wonka, Yiqun Wang
We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images.
1 code implementation • 12 Apr 2023 • Petr Mokrov, Alexander Korotin, Alexander Kolesov, Nikita Gushchin, Evgeny Burnaev
Energy-based models (EBMs) are known in the Machine Learning community for decades.
no code implementations • 14 Mar 2023 • Milena Gazdieva, Arip Asadulaev, Alexander Korotin, Evgeny Burnaev
We address this challenge and propose a novel theoretically-justified and lightweight unbalanced EOT solver.
no code implementations • 10 Mar 2023 • Maksim Nekrashevich, Alexander Korotin, Evgeny Burnaev
To demonstrate the effectiveness of our proposed method, we conduct experiments on the synthetic data and explore the practical applicability of our method to the popular task of the unsupervised alignment of word embeddings.
1 code implementation • 1 Mar 2023 • Elizaveta Kovtun, Galina Boeva, Artem Zabolotnyi, Evgeny Burnaev, Martin Spindler, Alexey Zaytsev
For example, the micro-AUC of our approach is $0. 9536$ compared to $0. 7501$ for a vanilla transformer.
1 code implementation • 13 Feb 2023 • Vladislav Zhuzhel, Vsevolod Grabar, Galina Boeva, Artem Zabolotnyi, Alexander Stepikin, Vladimir Zholobov, Maria Ivanova, Mikhail Orlov, Ivan Kireev, Evgeny Burnaev, Rodrigo Rivera-Castro, Alexey Zaytsev
Massive samples of event sequences data occur in various domains, including e-commerce, healthcare, and finance.
1 code implementation • 31 Jan 2023 • Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov
The method aims to provide topological similarity between the data manifold and its latent representation via enforcing the similarity in topological features (clusters, loops, 2D voids, etc.)
no code implementations • 30 Nov 2022 • Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey Nikolenko, Evgeny Burnaev
We apply topological data analysis (TDA) to speech classification problems and to the introspection of a pretrained speech model, HuBERT.
1 code implementation • NeurIPS 2023 • Nikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry Vetrov, Evgeny Burnaev
We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between continuous probability distributions which are accessible by samples.
no code implementations • 17 Oct 2022 • Timofey Grigoryev, Polina Verezemskaya, Mikhail Krinitskiy, Nikita Anikin, Alexander Gavrikov, Ilya Trofimov, Nikita Balabin, Aleksei Shpilman, Andrei Eremchenko, Sergey Gulev, Evgeny Burnaev, Vladimir Vanovskiy
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe.
1 code implementation • CVPR 2023 • Andreea Dogaru, Andrei Timotei Ardelean, Savva Ignatyev, Egor Zakharov, Evgeny Burnaev
In recent years, neural distance functions trained via volumetric ray marching have been widely adopted for multi-view 3D reconstruction.
no code implementations • 7 Sep 2022 • Egor Burkov, Ruslan Rakhimov, Aleksandr Safin, Evgeny Burnaev, Victor Lempitsky
Namely, we extend NeuS, a state-of-the-art neural implicit function formulation, to represent multiple objects of a class (human heads in our case) simultaneously.
2 code implementations • 31 Aug 2022 • Egor Shvetsov, Dmitry Osin, Alexey Zaytsev, Ivan Koryakovskiy, Valentin Buchnev, Ilya Trofimov, Evgeny Burnaev
The approach utilizes entropy regularization, quantization noise, and Adaptive Deviation for Quantization (ADQ) module to enhance the search procedure.
no code implementations • 27 Jun 2022 • Ilya Shashkov, Nikita Balabin, Evgeny Burnaev, Alexey Zaytsev
Our approach for the transfer learning of ensembles consists of two steps: (a) shifting weights of encoders of all models in the ensemble by a single shift vector and (b) doing a tiny fine-tuning for each individual model afterwards.
no code implementations • 21 Jun 2022 • Gleb Bazhenov, Sergei Ivanov, Maxim Panov, Alexey Zaytsev, Evgeny Burnaev
The problem of out-of-distribution detection for graph classification is far from being solved.
2 code implementations • 15 Jun 2022 • Alexander Korotin, Alexander Kolesov, Evgeny Burnaev
Despite the success of WGANs, it is still unclear how well the underlying OT dual solvers approximate the OT cost (Wasserstein-1 distance, $\mathbb{W}_{1}$) and the OT gradient needed to update the generator.
no code implementations • 6 Jun 2022 • Alexandr Notchenko, Vladislav Ishimtsev, Alexey Artemov, Vadim Selyutin, Emil Bogomolov, Evgeny Burnaev
We propose Scan2Part, a method to segment individual parts of objects in real-world, noisy indoor RGB-D scans.
no code implementations • 30 May 2022 • Arip Asadulaev, Alexander Korotin, Vage Egiazarian, Petr Mokrov, Evgeny Burnaev
We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals.
2 code implementations • 30 May 2022 • Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans.
1 code implementation • 19 May 2022 • Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova, Serguei Barannikov, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP.
Ranked #1 on Linguistic Acceptability on ItaCoLA
no code implementations • 14 May 2022 • Dmitrii Gavrilev, Nurlybek Amangeldiuly, Sergei Ivanov, Evgeny Burnaev
Prediction of protein-ligand (PL) binding affinity remains the key to drug discovery.
Ranked #2 on Protein-Ligand Affinity Prediction on CSAR-HiQ
1 code implementation • CVPR 2022 • Ruslan Rakhimov, Andrei-Timotei Ardelean, Victor Lempitsky, Evgeny Burnaev
We present a new system (NPBG++) for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time.
no code implementations • CVPR 2023 • Oleg Voynov, Gleb Bobrovskikh, Pavel Karpyshev, Saveliy Galochkin, Andrei-Timotei Ardelean, Arseniy Bozhenko, Ekaterina Karmanova, Pavel Kopanev, Yaroslav Labutin-Rymsho, Ruslan Rakhimov, Aleksandr Safin, Valerii Serpiva, Alexey Artemov, Evgeny Burnaev, Dzmitry Tsetserukou, Denis Zorin
We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks.
no code implementations • 2 Feb 2022 • Milena Gazdieva, Litu Rout, Alexander Korotin, Andrey Kravchenko, Alexander Filippov, Evgeny Burnaev
First, the learned SR map is always an optimal transport (OT) map.
1 code implementation • 28 Jan 2022 • Alexander Korotin, Vage Egiazarian, Lingxiao Li, Evgeny Burnaev
Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way.
3 code implementations • 28 Jan 2022 • Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs.
1 code implementation • 31 Dec 2021 • Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev
Comparison of data representations is a complex multi-aspect problem that has not enjoyed a complete solution yet.
no code implementations • 12 Oct 2021 • Ildar Abdrakhmanov, Evgenii Kanin, Sergei Boronin, Evgeny Burnaev, Andrei Osiptsov
We apply the transfer learning procedure to the transformer-based surrogate model, which includes the initial training on the dataset from a certain well and additional tuning of the model's weights on the dataset from a target well.
2 code implementations • ICLR 2022 • Litu Rout, Alexander Korotin, Evgeny Burnaev
In particular, we consider denoising, colorization, and inpainting, where the optimality of the restoration map is a desired attribute, since the output (restored) image is expected to be close to the input (degraded) one.
no code implementations • 29 Sep 2021 • Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev
We propose a method for comparing two data representations.
2 code implementations • EMNLP 2021 • Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content.
no code implementations • 2 Aug 2021 • Viktor Duplyakov, Anton Morozov, Dmitriy Popkov, Egor Shel, Albert Vainshtein, Evgeny Burnaev, Andrei Osiptsov, Grigory Paderin
We developed a set of methods including those based on the use of Euclidean distance and clustering techniques to perform similar (offset) wells search, which is useful for a field engineer to analyze earlier fracturing treatments on similar wells.
no code implementations • 23 Jul 2021 • Ivan Fursov, Alexey Zaytsev, Pavel Burnyshev, Ekaterina Dmitrieva, Nikita Klyuchnikov, Andrey Kravchenko, Ekaterina Artemova, Evgeny Burnaev
Moreover, due to the usage of the fine-tuned language model, the generated adversarial examples are hard to detect, thus current models are not robust.
no code implementations • 13 Jul 2021 • Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev
We present a pipeline for parametric wireframe extraction from densely sampled point clouds.
1 code implementation • 15 Jun 2021 • Ivan Fursov, Matvey Morozov, Nina Kaploukhaya, Elizaveta Kovtun, Rodrigo Rivera-Castro, Gleb Gusev, Dmitry Babaev, Ivan Kireev, Alexey Zaytsev, Evgeny Burnaev
In this work, we examine adversarial attacks on transaction records data and defences from these attacks.
2 code implementations • NeurIPS 2021 • Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov, Evgeny Burnaev
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
6 code implementations • NeurIPS 2021 • Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon, Alexander Filippov, Evgeny Burnaev
Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance.
3 code implementations • NeurIPS 2021 • Petr Mokrov, Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon, Evgeny Burnaev
Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over entropy functionals in Wasserstein space.
1 code implementation • 25 May 2021 • Aleksandr Safin, Maxim Kan, Nikita Drobyshev, Oleg Voynov, Alexey Artemov, Alexander Filippov, Denis Zorin, Evgeny Burnaev
We propose an unpaired learning method for depth super-resolution, which is based on a learnable degradation model, enhancement component and surface normal estimates as features to produce more accurate depth maps.
1 code implementation • NeurIPS 2021 • Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov, Evgeny Burnaev
We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
no code implementations • 3 Apr 2021 • Vladislav Zhuzhel, Rodrigo Rivera-Castro, Nina Kaploukhaya, Liliya Mironova, Alexey Zaytsev, Evgeny Burnaev
Cohort analysis is a pervasive activity in web analytics.
2 code implementations • ICLR 2021 • Alexander Korotin, Lingxiao Li, Justin Solomon, Evgeny Burnaev
Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport.
no code implementations • 13 Jan 2021 • Tsimboy Olga, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets
In this work we derive analytical expression for the Denoising Score matching using the Kernel Exponential Family as a model distribution.
no code implementations • 31 Dec 2020 • Serguei Barannikov, Daria Voronkova, Ilya Trofimov, Alexander Korotin, Grigorii Sotnikov, Evgeny Burnaev
We define the neural network Topological Obstructions score, "TO-score", with the help of robust topological invariants, barcodes of the loss function, that quantify the "badness" of local minima for gradient-based optimization.
no code implementations • 17 Dec 2020 • Artem Sevastopolsky, Savva Ignatiev, Gonzalo Ferrer, Evgeny Burnaev, Victor Lempitsky
The model is fitted to the sequence of frames with human face-specific priors that enforce the plausibility of albedo-lighting decomposition and operates at the interactive frame rate.
1 code implementation • 7 Dec 2020 • Anton Smerdov, Evgeny Burnaev, Andrey Somov, Anton Stepanov
For this reason, we collected the physiological, environmental, and the game chair data from Pro and amateur players.
1 code implementation • CVPR 2021 • Alexey Bokhovkin, Vladislav Ishimtsev, Emil Bogomolov, Denis Zorin, Alexey Artemov, Evgeny Burnaev, Angela Dai
Recent advances in 3D semantic scene understanding have shown impressive progress in 3D instance segmentation, enabling object-level reasoning about 3D scenes; however, a finer-grained understanding is required to enable interactions with objects and their functional understanding.
1 code implementation • 30 Nov 2020 • Albert Matveev, Ruslan Rakhimov, Alexey Artemov, Gleb Bobrovskikh, Vage Egiazarian, Emil Bogomolov, Daniele Panozzo, Denis Zorin, Evgeny Burnaev
We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes.
no code implementations • 30 Nov 2020 • Oleg Voynov, Aleksandr Safin, Savva Ignatyev, Evgeny Burnaev
We study the effects of the additional input to deep multi-view stereo methods in the form of low-quality sensor depth.
1 code implementation • 29 Nov 2020 • Anton Smerdov, Andrey Somov, Evgeny Burnaev, Bo Zhou, Paul Lukowicz
In this article, we propose the methods based on the sensor data analysis for predicting whether a player will win the future encounter.
BIG-bench Machine Learning Interpretable Machine Learning +8
1 code implementation • 20 Oct 2020 • Ruslan Aliev, Ekaterina Kondrateva, Maxim Sharaev, Oleg Bronov, Alexey Marinets, Sergey Subbotin, Alexander Bernstein, Evgeny Burnaev
Focal cortical dysplasia (FCD) is one of the most common epileptogenic lesions associated with cortical development malformations.
1 code implementation • 14 Oct 2020 • Marina Pominova, Ekaterina Kondrateva, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev
ABIDE is the largest open-source autism spectrum disorder database with both fMRI data and full phenotype description.
1 code implementation • 14 Oct 2020 • Ekaterina Kondrateva, Marina Pominova, Elena Popova, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev
Machine learning and computer vision methods are showing good performance in medical imagery analysis.
no code implementations • 7 Oct 2020 • Ivan Makhotin, Denis Orlov, Dmitry Koroteev, Evgeny Burnaev, Aram Karapetyan, Dmitry Antonenko
In this work, we present a data-driven technique for oil recovery factor estimation using reservoir parameters and representative statistics.
no code implementations • 8 Sep 2020 • Rodrigo Rivera-Castro, Aleksandr Pletnev, Polina Pilyugina, Grecia Diaz, Ivan Nazarov, Wanyi Zhu, Evgeny Burnaev
Topological Data Analysis (TDA) is a recent approach to analyze data sets from the perspective of their topological structure.
no code implementations • 8 Sep 2020 • Aleksandr Pletnev, Rodrigo Rivera-Castro, Evgeny Burnaev
The results show the relevancy and suitability of GNN as methods for model recommendations in time series forecasting.
Applications
no code implementations • 7 Sep 2020 • Rodrigo Rivera-Castro, Polina Pilyugina, Evgeny Burnaev
Portfolio management is essential for any investment decision.
no code implementations • 7 Sep 2020 • Ivan Maksimov, Rodrigo Rivera-Castro, Evgeny Burnaev
Recommender systems have become an essential instrument in a wide range of industries to personalize the user experience.
no code implementations • 27 Aug 2020 • Aiusha Sangadiev, Rodrigo Rivera-Castro, Kirill Stepanov, Andrey Poddubny, Kirill Bubenchikov, Nikita Bekezin, Polina Pilyugina, Evgeny Burnaev
Further, we use DeepFolio for optimal portfolio allocation of crypto-assets with rebalancing.
1 code implementation • ECCV 2020 • Vladislav Ishimtsev, Alexey Bokhovkin, Alexey Artemov, Savva Ignatyev, Matthias Niessner, Denis Zorin, Evgeny Burnaev
Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios.
no code implementations • 6 Jul 2020 • Albert Matveev, Alexey Artemov, Denis Zorin, Evgeny Burnaev
Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline.
1 code implementation • 26 Jun 2020 • Ruslan Rakhimov, Emil Bogomolov, Alexandr Notchenko, Fung Mao, Alexey Artemov, Denis Zorin, Evgeny Burnaev
DensePose estimation task is a significant step forward for enhancing user experience computer vision applications ranging from augmented reality to cloth fitting.
1 code implementation • 20 Jun 2020 • Maxim Kan, Ruslan Aliev, Anna Rudenko, Nikita Drobyshev, Nikita Petrashen, Ekaterina Kondrateva, Maxim Sharaev, Alexander Bernstein, Evgeny Burnaev
Deep learning shows high potential for many medical image analysis tasks.
1 code implementation • 18 Jun 2020 • Ruslan Rakhimov, Denis Volkhonskiy, Alexey Artemov, Denis Zorin, Evgeny Burnaev
After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner.
Ranked #13 on Video Prediction on Kinetics-600 12 frames, 64x64
1 code implementation • 15 Jun 2020 • Ilya Trofimov, Nikita Klyuchnikov, Mikhail Salnikov, Alexander Filippov, Evgeny Burnaev
The method relies on a new approach to low-fidelity evaluations of neural architectures by training for a few epochs using a knowledge distillation.
1 code implementation • 12 Jun 2020 • Nikita Klyuchnikov, Ilya Trofimov, Ekaterina Artemova, Mikhail Salnikov, Maxim Fedorov, Evgeny Burnaev
In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP).
1 code implementation • MIDL 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.
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.
1 code implementation • 25 Mar 2020 • Ivan Nazarov, Evgeny Burnaev
With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation.
1 code implementation • 23 Mar 2020 • Ekaterina Artemova, Amir Bakarov, Aleksey Artemov, Evgeny Burnaev, Maxim Sharaev
In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics.
no code implementations • 22 Mar 2020 • Dmitrii Smolyakov, Evgeny Burnaev
In this paper, we present a monitoring system that allows increasing road safety by predicting ice formation.
1 code implementation • ECCV 2020 • Vage Egiazarian, Oleg Voynov, Alexey Artemov, Denis Volkhonskiy, Aleksandr Safin, Maria Taktasheva, Denis Zorin, Evgeny Burnaev
We present a new method for vectorization of technical line drawings, such as floor plans, architectural drawings, and 2D CAD images.
no code implementations • 9 Mar 2020 • Ivan Fursov, Alexey Zaytsev, Nikita Kluchnikov, Andrey Kravchenko, Evgeny Burnaev
The first approach adopts a Monte-Carlo method and allows usage in any scenario, the second approach uses a continuous relaxation of models and target metrics, and thus allows usage of state-of-the-art methods for adversarial attacks with little additional effort.
no code implementations • 7 Mar 2020 • Nina Mazyavkina, Sergey Sviridov, Sergei Ivanov, Evgeny Burnaev
Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution.
no code implementations • 15 Dec 2019 • Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev
In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts.
1 code implementation • 13 Dec 2019 • Vage Egiazarian, Savva Ignatyev, Alexey Artemov, Oleg Voynov, Andrey Kravchenko, Youyi Zheng, Luiz Velho, Evgeny Burnaev
Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design.
no code implementations • 11 Dec 2019 • Yermek Kapushev, Ivan Oseledets, Evgeny Burnaev
In this paper, we consider the tensor completion problem representing the solution in the tensor train (TT) format.
no code implementations • 29 Nov 2019 • Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev
We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces.
1 code implementation • 5 Nov 2019 • Sergey Pavlov, Alexey Artemov, Maksim Sharaev, Alexander Bernstein, Evgeny Burnaev
Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain.
2 code implementations • 5 Nov 2019 • Marina Pominova, Ekaterina Kondrateva, Maksim Sharaev, Sergey Pavlov, Alexander Bernstein, Evgeny Burnaev
Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis.
1 code implementation • 26 Oct 2019 • Sergei Ivanov, Sergei Sviridov, Evgeny Burnaev
In recent years there has been a rapid increase in classification methods on graph structured data.
no code implementations • pproximateinference AABI Symposium 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Variational Auto Encoders (VAE) are capable of generating realistic images, sounds and video sequences.
4 code implementations • ICLR 2021 • Alexander Korotin, Vage Egiazarian, Arip Asadulaev, Alexander Safin, Evgeny Burnaev
We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance).
no code implementations • 25 Sep 2019 • Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev
We apply canonical forms of gradient complexes (barcodes) to explore neural networks loss surfaces.
1 code implementation • NeurIPS 2021 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
We learn the approximation of the aggregated posterior as a prior for each task.
1 code implementation • 18 Aug 2019 • Anton Smerdov, Anastasia Kiskun, Rostislav Shaniiazov, Andrey Somov, Evgeny Burnaev
eSports is the rapidly developing multidisciplinary domain.
1 code implementation • 18 Aug 2019 • Anton Smerdov, Evgeny Burnaev, Andrey Somov
Today's competition between the professional eSports teams is so strong that in-depth analysis of players' performance literally crucial for creating a powerful team.
no code implementations • 15 Aug 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.
no code implementations • 1 Jul 2019 • Maria Taktasheva, Albert Matveev, Alexey Artemov, Evgeny Burnaev
Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions.
no code implementations • 28 May 2019 • Evgeny Burnaev
In this paper, we consider a problem of failure prediction in the context of predictive maintenance applications.
no code implementations • 26 May 2019 • Rodrigo Rivera-Castro, Polina Pilyugina, Alexander Pletnev, Ivan Maksimov, Wanyi Wyz, Evgeny Burnaev
Topological Data Analysis (TDA) is a recent approach to analyze data sets from the perspective of their topological structure.
no code implementations • 25 May 2019 • Marina Pominova, Anna Kuzina, Ekaterina Kondrateva, Svetlana Sushchinskaya, Maxim Sharaev, Evgeny Burnaev, and Vyacheslav Yarkin
In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health.
no code implementations • 23 May 2019 • Evgenii Kanin, Andrei Osiptsov, Albert Vainshtein, Evgeny Burnaev
In order to extend the applicability and the accuracy of the existing accessible methods, a method of pressure drop calculation in the pipeline is proposed.
no code implementations • 20 May 2019 • Evgenii Egorov, Kirill Neklydov, Ruslan Kostoev, Evgeny Burnaev
One of the core problems in variational inference is a choice of approximate posterior distribution.
1 code implementation • 20 May 2019 • Maria Kolos, Anton Marin, Alexey Artemov, Evgeny Burnaev
Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant.
no code implementations • 20 May 2019 • Oleg Sudakov, Dmitri Koroteev, Boris Belozerov, Evgeny Burnaev
We develop a data-driven model, introducing recent advances in machine learning to reservoir simulation.
no code implementations • 20 May 2019 • Rodrigo Rivera-Castro, Ivan Nazarov, Yuke Xiang, Alexander Pletneev, Ivan Maksimov, Evgeny Burnaev
Due to their nature, they differ significantly from traditional supply chains.
3 code implementations • 20 May 2019 • Alexey Bokhovkin, Evgeny Burnaev
Convolutional neural networks are powerful visual models that yield hierarchies of features and practitioners widely use them to process remote sensing data.
no code implementations • 14 May 2019 • Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin
Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections.
no code implementations • 9 Apr 2019 • Aibek Alanov, Max Kochurov, Denis Volkhonskiy, Daniil Yashkov, Evgeny Burnaev, Dmitry Vetrov
We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism.
no code implementations • 27 Mar 2019 • Evgenya Romanenkova, Alexey Zaytsev, Nikita Klyuchnikov, Arseniy Gruzdev, Ksenia Antipova, Leyla Ismailova, Evgeny Burnaev, Artyom Semenikhin, Vitaliy Koryabkin, Igor Simon, Dmitry Koroteev
During the directional drilling, a bit may sometimes go to a nonproductive rock layer due to the gap about 20m between the bit and high-fidelity rock type sensors.
no code implementations • 27 Feb 2019 • Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev
The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback.
no code implementations • 5 Feb 2019 • Ivan Makhotin, Dmitry Koroteev, Evgeny Burnaev
We discuss the potential for further development of ML techniques for predicting changes in oil rate after HF.
no code implementations • 29 Jan 2019 • Denis Volkhonskiy, Ekaterina Muravleva, Oleg Sudakov, Denis Orlov, Boris Belozerov, Evgeny Burnaev, Dmitry Koroteev
In many branches of earth sciences, the problem of rock study on the micro-level arises.
no code implementations • 8 Jan 2019 • Pavel Temirchev, Maxim Simonov, Ruslan Kostoev, Evgeny Burnaev, Ivan Oseledets, Alexey Akhmetov, Andrey Margarit, Alexander Sitnikov, Dmitry Koroteev
We present a novel technique for assessing the dynamics of multiphase fluid flow in the oil reservoir.
2 code implementations • ICCV 2019 • Oleg Voynov, Alexey Artemov, Vage Egiazarian, Alexander Notchenko, Gleb Bobrovskikh, Denis Zorin, Evgeny Burnaev
RGBD images, combining high-resolution color and lower-resolution depth from various types of depth sensors, are increasingly common.
3 code implementations • CVPR 2019 • Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo
We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications.
1 code implementation • 13 Sep 2018 • Nikita Klyuchnikov, Evgeny Burnaev
In this paper we address a classification problem where two sources of labels with different levels of fidelity are available.
1 code implementation • ICLR 2019 • ShahRukh Athar, Evgeny Burnaev, Victor Lempitsky
The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the latent space to the image space.
no code implementations • 8 Jun 2018 • Nikita Klyuchnikov, Alexey Zaytsev, Arseniy Gruzdev, Georgiy Ovchinnikov, Ksenia Antipova, Leyla Ismailova, Ekaterina Muravleva, Evgeny Burnaev, Artyom Semenikhin, Alexey Cherepanov, Vitaliy Koryabkin, Igor Simon, Alexey Tsurgan, Fedor Krasnov, Dmitry Koroteev
Directional oil well drilling requires high precision of the wellbore positioning inside the productive area.
2 code implementations • ICML 2018 • Sergey Ivanov, Evgeny Burnaev
The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data.
Ranked #17 on Graph Classification on IMDb-B
no code implementations • 26 Apr 2018 • Alexander Bernstein, Evgeny Burnaev, Ekaterina Kondratyeva, Svetlana Sushchinskaya, Maxim Sharaev, Alexander Andreev, Alexey Artemov, Renat Akzhigitov
We consider a problem of diagnostic pattern recognition/classification from neuroimaging data.
no code implementations • 26 Apr 2018 • Maxim Sharaev, Alexander Andreev, Alexey Artemov, Alexander Bernstein, Evgeny Burnaev, Ekaterina Kondratyeva, Svetlana Sushchinskaya, Renat Akzhigitov
As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression.
no code implementations • 18 Mar 2018 • Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev
The first one is theoretically close to an optimal algorithm and is based on replication of independent copies.
no code implementations • 14 Mar 2018 • Vladimir Ignatiev, Alexey Trekin, Viktor Lobachev, Georgy Potapov, Evgeny Burnaev
Recent developments in the remote sensing systems and image processing made it possible to propose a new method of the object classification and detection of the specific changes in the series of satellite Earth images (so called targeted change detection).
no code implementations • 2 Mar 2018 • Oleg Sudakov, Evgeny Burnaev, Dmitry Koroteev
We present a research study aimed at testing of applicability of machine learning techniques for prediction of permeability of digitized rock samples.
no code implementations • 19 Feb 2018 • Alexey Trekin, German Novikov, Georgy Potapov, Vladimir Ignatiev, Evgeny Burnaev
When major disaster occurs the questions are raised how to estimate the damage in time to support the decision making process and relief efforts by local authorities or humanitarian teams.
2 code implementations • ICLR 2018 • Marina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets
We consider the problem of improving kernel approximation via randomized feature maps.
no code implementations • 8 Nov 2017 • Alexander Korotin, Vladimir V'yugin, Evgeny Burnaev
In the first one, at each step $t$ the learner has to combine the point forecasts of the experts issued for the time interval $[t+1, t+d]$ ahead.
no code implementations • 16 Sep 2017 • Rodrigo Rivera, Evgeny Burnaev
This paper argues that there has not been enough discussion in the field of applications of Gaussian Process for the fast moving consumer goods industry.
no code implementations • 12 Jul 2017 • Evgeny Burnaev, Pavel Erofeev, Dmitry Smolyakov
Anomaly detection based on one-class classification algorithms is broadly used in many applied domains like image processing (e. g. detection of whether a patient is "cancerous" or "healthy" from mammography image), network intrusion detection, etc.
no code implementations • 12 Jul 2017 • Evgeny Burnaev, Pavel Erofeev, Artem Papanov
In many real-world binary classification tasks (e. g. detection of certain objects from images), an available dataset is imbalanced, i. e., it has much less representatives of a one class (a minor class), than of another.
no code implementations • 12 Jul 2017 • Evgeny Burnaev, Alexey Zaytsev
Engineers widely use Gaussian process regression framework to construct surrogate models aimed to replace computationally expensive physical models while exploring design space.
no code implementations • 17 Jun 2017 • Alexander Kuleshov, Alexander Bernstein, Evgeny Burnaev, Yury Yanovich
The latter allows solving the robot localization problem as the Kalman filtering problem.
no code implementations • 11 Jun 2017 • Vladislav Ishimtsev, Ivan Nazarov, Alexander Bernstein, Evgeny Burnaev
Anomalies in time-series data give essential and often actionable information in many applications.
no code implementations • 11 Jun 2017 • Denis Volkhonskiy, Ilia Nouretdinov, Alexander Gammerman, Vladimir Vovk, Evgeny Burnaev
We consider the problem of quickest change-point detection in data streams.
1 code implementation • 6 Jun 2017 • Smolyakov Dmitry, Alexander Korotin, Pavel Erofeev, Artem Papanov, Evgeny Burnaev
One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i. e., to drop some of its elements or to synthesize new ones.
1 code implementation • 16 Mar 2017 • Denis Volkhonskiy, Ivan Nazarov, Evgeny Burnaev
Steganography is collection of methods to hide secret information ("payload") within non-secret information "container").
no code implementations • 28 Nov 2016 • Alexandr Notchenko, Ermek Kapushev, Evgeny Burnaev
In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a large-scale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape.
no code implementations • 21 Oct 2016 • Alexey Zaytsev, Evgeny Burnaev
The key question in this setting is how the sizes of the high and low fidelity data samples should be selected in order to stay within a given computational budget and maximize accuracy of the regression model prior to committing resources on data acquisition.
no code implementations • 26 Sep 2016 • Evgeny Burnaev, Dmitry Smolyakov
A number of important applied problems in engineering, finance and medicine can be formulated as a problem of anomaly detection.
no code implementations • 26 Sep 2016 • Evgeny Burnaev, Ivan Koptelov, German Novikov, Timur Khanipov
Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction.
no code implementations • 19 Sep 2016 • Evgeny Burnaev, Ivan Nazarov
General predictive models do not provide a measure of confidence in predictions without Bayesian assumptions.
1 code implementation • 5 Sep 2016 • Mikhail Belyaev, Evgeny Burnaev, Ermek Kapushev, Maxim Panov, Pavel Prikhodko, Dmitry Vetrov, Dmitry Yarotsky
We describe GTApprox - a new tool for medium-scale surrogate modeling in industrial design.
no code implementations • 16 Aug 2016 • Evgeny Burnaev, Vladislav Ishimtsev
Anomalies (unusual patterns) in time-series data give essential, and often actionable information in critical situations.
no code implementations • 8 Apr 2014 • Evgeny Burnaev, Vladimir Vovk
Conformal prediction is a method of producing prediction sets that can be applied on top of a wide range of prediction algorithms.