1 code implementation • 24 Nov 2022 • Alexandra Senderovich, Ekaterina Bulatova, Anton Obukhov, Maxim Rakhuba
We demonstrate the improved properties of modern CNNs with our method and analyze its impact on the model performance, calibration, and adversarial robustness.
1 code implementation • ICCV 2021 • Mikhail Usvyatsov, Anastasia Makarova, Rafael Ballester-Ripoll, Maxim Rakhuba, Andreas Krause, Konrad Schindler
We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only.
no code implementations • 27 Mar 2021 • Alexander Novikov, Maxim Rakhuba, Ivan Oseledets
In scientific computing and machine learning applications, matrices and more general multidimensional arrays (tensors) can often be approximated with the help of low-rank decompositions.
1 code implementation • 7 Mar 2021 • Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, Luc van Gool
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context.
1 code implementation • ICML 2020 • Anton Obukhov, Maxim Rakhuba, Stamatios Georgoulis, Menelaos Kanakis, Dengxin Dai, Luc van Gool
Each of the tensors in the set is modeled using Tensor Rings, though the concept applies to other Tensor Networks.