Research
I am broadly interested in deep learning, generative models, and Bayesian modeling. I mostly work on visual perception and learning from a small amount of data/labels.
|
|
The Deep Weight Prior
Andrei Atanov*,
Arsenii Ashukha*,
Kirill Struminsky,
Dmitry Vetrov,
Max Welling,
ICLR, 2019
We propose a flexible prior distribution over convolutional kernels of Bayesian neural networks.
|
|
Semi-Conditional Normalizing Flows for Semi-Supervised Learning
Andrei Atanov,
Alexandra Volokhova,
Arsenii Ashukha,
Ivan Sosnovik,
Dmitry Vetrov,
INNF Workshop at ICML, 2019
We apply conditional normalizing flows to semi-supervised learning. We utilize multiscale architecture for computational efficiency.
|
|
Uncertainty Estimation via Stochastic Batch Normalization
Andrei Atanov,
Arsenii Ashukha,
Dmitry Molchanov,
Kirill Neklyudov,
Dmitry Vetrov,
ICLR Workshop Track, 2018
We propose a probabilistic view on Batch Normalization and an efficient test-time averaging technique for uncertainty estimation in batch-normalized DNNs.
|
|