30 citations · 190 across the 36 of their papers we have counts for
8 papers · 1 filter
Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2
Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. Th…
Generation of the NIR spectral Band for Satellite Images with Convolutional Neural Networks
Svetlana Illarionova, Dmitrii Shadrin, Alexey Trekin +2
The near-infrared (NIR) spectral range (from 780 to 2500 nm) of the multispectral remote sensing imagery provides vital information for the landcover classification, especially con…
Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Anh-Huy Phan, Konstantin Sobolev, Konstantin Sozykin +6
Most state of the art deep neural networks are overparameterized and exhibit a high computational cost. A straightforward approach to this problem is to replace convolutional kerne…
Bayesian aggregation improves traditional single image crop classification approaches
Ivan Matvienko, Mikhail Gasanov, Anna Petrovskaia +3
Machine learning (ML) methods and neural networks (NN) are widely implemented for crop types recognition and classification based on satellite images. However, most of these studie…
Recognition of Russian traffic signs in winter conditions. Solutions of the "Ice Vision" competition winners
Artem L. Pavlov, Azat Davletshin, Alexey Kharlamov +8
With the advancements of various autonomous car projects aiming to achieve SAE Level 5, real-time detection of traffic signs in real-life scenarios has become a highly relevant pro…
Hyperbolic Image Embeddings
Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova +2
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…