1 code implementation • 9 Apr 2024 • Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub M Tomczak
We model gradient updates as a probabilistic model and utilize stochastic variational inference (SVI) to derive an efficient and effective update rule.
no code implementations • 27 Mar 2023 • Michał Zając, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzciński, Florian Shkurti, Piotr Miłoś
Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data.
1 code implementation • 20 Feb 2023 • Anna Kuzina, Jakub M. Tomczak
Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models.
no code implementations • 28 Jun 2022 • Anna Kuzina, Kumar Pratik, Fabio Valerio Massoli, Arash Behboodi
In compressed sensing, the goal is to reconstruct the signal from an underdetermined system of linear measurements.
1 code implementation • 31 May 2022 • Kamil Deja, Anna Kuzina, Tomasz Trzciński, Jakub M. Tomczak
Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal.
1 code implementation • 18 Mar 2022 • Anna Kuzina, Max Welling, Jakub M. Tomczak
Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations.
1 code implementation • 10 Mar 2021 • Anna Kuzina, Max Welling, Jakub M. Tomczak
In this work, we explore adversarial attacks on the Variational Autoencoders (VAE).
1 code implementation • ICLR 2022 • David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.
Ranked #5 on Sequential Image Classification on Sequential MNIST
1 code implementation • MIDL 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.
no code implementations • pproximateinference AABI Symposium 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Variational Auto Encoders (VAE) are capable of generating realistic images, sounds and video sequences.
1 code implementation • NeurIPS 2021 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
We learn the approximation of the aggregated posterior as a prior for each task.
no code implementations • 15 Aug 2019 • Anna Kuzina, Evgenii Egorov, Evgeny Burnaev
Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods.
no code implementations • 25 May 2019 • Marina Pominova, Anna Kuzina, Ekaterina Kondrateva, Svetlana Sushchinskaya, Maxim Sharaev, Evgeny Burnaev, and Vyacheslav Yarkin
In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health.