Search Results for author: Valentin Khrulkov

Found 20 papers, 13 papers with code

Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models

1 code implementation10 Apr 2023 Nikita Starodubcev, Dmitry Baranchuk, Valentin Khrulkov, Artem Babenko

Finally, we show that our approach can adapt the pretrained model to the user-specified image and text description on the fly just for 4 seconds.

Image Manipulation

Understanding DDPM Latent Codes Through Optimal Transport

no code implementations14 Feb 2022 Valentin Khrulkov, Gleb Ryzhakov, Andrei Chertkov, Ivan Oseledets

Diffusion models have recently outperformed alternative approaches to model the distribution of natural images, such as GANs.

Label-Efficient Semantic Segmentation with Diffusion Models

1 code implementation ICLR 2022 Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov, Valentin Khrulkov, Artem Babenko

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance.

Denoising Segmentation +2

Latent Transformations via NeuralODEs for GAN-based Image Editing

1 code implementation ICCV 2021 Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets, Artem Babenko

Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN.

Attribute

Revisiting Deep Learning Models for Tabular Data

10 code implementations NeurIPS 2021 Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, Artem Babenko

The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets.

Neural Side-by-Side: Predicting Human Preferences for No-Reference Super-Resolution Evaluation

1 code implementation CVPR 2021 Valentin Khrulkov, Artem Babenko

Given the dataset and the labels, we trained a CNN model that obtains a pair of images and for each image predicts a probability of being more preferable than its counterpart.

SSIM Super-Resolution

Disentangled Representations from Non-Disentangled Models

no code implementations11 Feb 2021 Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets, Artem Babenko

Constructing disentangled representations is known to be a difficult task, especially in the unsupervised scenario.

Disentanglement Fairness

Functional Space Analysis of Local GAN Convergence

no code implementations8 Feb 2021 Valentin Khrulkov, Artem Babenko, Ivan Oseledets

Recent work demonstrated the benefits of studying continuous-time dynamics governing the GAN training.

Data Augmentation

Tensorized Embedding Layers

no code implementations Findings of the Association for Computational Linguistics 2020 Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova, Ivan Oseledets

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing.

Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks

1 code implementation15 Aug 2020 Leyla Mirvakhabova, Evgeny Frolov, Valentin Khrulkov, Ivan Oseledets, Alexander Tuzhilin

We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem.

Collaborative Filtering

Sample Efficient Ensemble Learning with Catalyst.RL

2 code implementations29 Mar 2020 Sergey Kolesnikov, Valentin Khrulkov

We present Catalyst. RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research.

Ensemble Learning reinforcement-learning +1

Universality Theorems for Generative Models

no code implementations27 May 2019 Valentin Khrulkov, Ivan Oseledets

Despite the fact that generative models are extremely successful in practice, the theory underlying this phenomenon is only starting to catch up with practice.

Hyperbolic Image Embeddings

3 code implementations CVPR 2020 Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, Victor Lempitsky

Computer vision tasks such as image classification, image retrieval and few-shot learning are currently dominated by Euclidean and spherical embeddings, so that the final decisions about class belongings or the degree of similarity are made using linear hyperplanes, Euclidean distances, or spherical geodesic distances (cosine similarity).

Few-Shot Learning General Classification +3

Tensorized Embedding Layers for Efficient Model Compression

1 code implementation30 Jan 2019 Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova, Ivan Oseledets

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing.

Language Modelling Machine Translation +2

Geometry Score: A Method For Comparing Generative Adversarial Networks

1 code implementation ICML 2018 Valentin Khrulkov, Ivan Oseledets

One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse.

Tensor Train decomposition on TensorFlow (T3F)

2 code implementations5 Jan 2018 Alexander Novikov, Pavel Izmailov, Valentin Khrulkov, Michael Figurnov, Ivan Oseledets

Tensor Train decomposition is used across many branches of machine learning.

Mathematical Software Numerical Analysis

Expressive power of recurrent neural networks

2 code implementations ICLR 2018 Valentin Khrulkov, Alexander Novikov, Ivan Oseledets

In this paper, we prove the expressive power theorem (an exponential lower bound on the width of the equivalent shallow network) for a class of recurrent neural networks -- ones that correspond to the Tensor Train (TT) decomposition.

Tensor Decomposition

Art of singular vectors and universal adversarial perturbations

no code implementations CVPR 2018 Valentin Khrulkov, Ivan Oseledets

Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.