1.1k citations
- Lomonosov Moscow State UniversityRU146 papers
- Yandex School of Data AnalysisRU143 papers
- Centre National de la Recherche ScientifiqueFR136 papers
- University of ZurichCH136 papers
- European Organization for Nuclear ResearchCH135 papers
- Imperial College LondonGB134 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR134 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT134 papers
- Laboratoire de Physique Nucléaire et de Hautes ÉnergiesFR134 papers
- École Polytechnique Fédérale de LausanneCH133 papers
- Institute for High Energy PhysicsES133 papers
- Institute for Nuclear ResearchRU133 papers
11 papers · 1 filter
Latent Transformations via NeuralODEs for GAN-based Image Editing
Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets +1
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. Speci…
StyleGAN2 Distillation for Feed-forward Image Manipulation
Yuri Viazovetskyi, Vladimir Ivashkin, Evgeny Kashin
StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient i…
Precipitation Nowcasting with Satellite Imagery
Vadim Lebedev, Vladimir Ivashkin, Irina Rudenko +6
Precipitation nowcasting is a short-range forecast of rain/snow (up to 2 hours), often displayed on top of the geographical map by the weather service. Modern precipitation nowcast…
Impostor Networks for Fast Fine-Grained Recognition
Vadim Lebedev, Artem Babenko, Victor Lempitsky
In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, maki…
Parsing Images of Overlapping Organisms with Deep Singling-Out Networks
Victor Yurchenko, Victor Lempitsky
This work is motivated by the mostly unsolved task of parsing biological images with multiple overlapping articulated model organisms (such as worms or larvae). We present a genera…
Spatially Adaptive Computation Time for Residual Networks
Michael Figurnov, Maxwell D. Collins, Yukun Zhu +4
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is…