233 citations · 1.1k across the 115 of their papers we have counts for
18 papers · 1 filter
Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds
Vage Egiazarian, Savva Ignatyev, Alexey Artemov +5
Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despit…
Tensor Completion via Gaussian Process Based Initialization
Yermek Kapushev, Ivan Oseledets, Evgeny Burnaev
In this paper, we consider the tensor completion problem representing the solution in the tensor train (TT) format. It is assumed that tensor is high-dimensional, and tensor values…
Barcodes as Summary of Loss Function Topology
Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan +2
We propose to study neural networks' loss surfaces by methods of topological data analysis. We suggest to apply barcodes of Morse complexes to explore topology of loss surfaces. An…
Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem
Sergey Pavlov, Alexey Artemov, Maksim Sharaev +2
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…
3D Deformable Convolutions for MRI classification
Marina Pominova, Ekaterina Kondrateva, Maksim Sharaev +3
Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neura…
Wasserstein-2 Generative Networks
Alexander Korotin, Vage Egiazarian, Arip Asadulaev +2
We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural…