128 citations · 233 across the 7 of their papers we have counts for
7 papers
Schrödinger Bridge Flow for Unpaired Data Translation
Valentin De Bortoli, Iryna Korshunova, Andriy Mnih +1
Mass transport problems arise in many areas of machine learning whereby one wants to compute a map transporting one distribution to another. Generative modeling techniques like Gen…
A Closer Look at the Adversarial Robustness of Information Bottleneck Models
Iryna Korshunova, David Stutz, Alexander A. Alemi +2
We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks ca…
Discriminative Topic Modeling with Logistic LDA
Iryna Korshunova, Hanchen Xiong, Mateusz Fedoryszak +1
Despite many years of research into latent Dirichlet allocation (LDA), applying LDA to collections of non-categorical items is still challenging. Yet many problems with much richer…
BRUNO: A Deep Recurrent Model for Exchangeable Data
Iryna Korshunova, Jonas Degrave, Ferenc Huszár +3
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations. Our model is provab…
Faster gaze prediction with dense networks and Fisher pruning
Lucas Theis, Iryna Korshunova, Alykhan Tejani +1
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in…
Fast Face-swap Using Convolutional Neural Networks
Iryna Korshunova, Wenzhe Shi, Joni Dambre +1
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting. To perform…
Music transcription modelling and composition using deep learning
Bob L. Sturm, João Felipe Santos, Oded Ben-Tal +1
We apply deep learning methods, specifically long short-term memory (LSTM) networks, to music transcription modelling and composition. We build and train LSTM networks using approx…