330 citations · 358 across the 13 of their papers we have counts for
13 papers · 1 filter
Memory-efficient particle filter recurrent neural network for object localization
Roman Korkin, Ivan Oseledets, Aleksandr Katrutsa
This study proposes a novel memory-efficient recurrent neural network (RNN) architecture specified to solve the object localization problem. This problem is to recover the object s…
On the structure of the Schur complement matrix for the Stokes equation
Vladislav Pimanov, Ekaterina Muravleva, Ivan Oseledets +1
In this paper, we investigate the structure of the Schur complement matrix for the fully-staggered finite-difference discretization of the stationary Stokes equation. Specifically,…
Unsupervised evaluation of GAN sample quality: Introducing the TTJac Score
Egor Sevriugov, Ivan Oseledets
Evaluation metrics are essential for assessing the performance of generative models in image synthesis. However, existing metrics often involve high memory and time consumption as…
Robust GAN inversion
Egor Sevriugov, Ivan Oseledets
Recent advancements in real image editing have been attributed to the exploration of Generative Adversarial Networks (GANs) latent space. However, the main challenge of this proced…
Quantization Aware Factorization for Deep Neural Network Compression
Daria Cherniuk, Stanislav Abukhovich, Anh-Huy Phan +3
Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitatio…
Efficient GPT Model Pre-training using Tensor Train Matrix Representation
Viktoriia Chekalina, Georgii Novikov, Julia Gusak +2
Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their…