Sebastian Nowozin

is this you? claim profile

∙ 0 followers
Google ∙ Microsoft

Principal Researcher at Microsoft Research, Cambridge, UK, managing the Machine Intelligence and Perception group.

How Good is the Bayes Posterior in Deep Neural Networks Really?

During the past five years the Bayesian deep learning community has deve...
02/06/2020 ∙ by Florian Wenzel, et al. ∙ 27 ∙ share

read it
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations

Recently there has been an increased interest in unsupervised learning o...
09/05/2019 ∙ by Jan Stühmer, et al. ∙ 24 ∙ share

read it
Contextual Face Recognition with a Nested-Hierarchical Nonparametric Identity Model

Current face recognition systems typically operate via classification in...
11/19/2018 ∙ by Daniel C. Castro, et al. ∙ 14 ∙ share

read it
TaskNorm: Rethinking Batch Normalization for Meta-Learning

Modern meta-learning approaches for image classification rely on increas...
03/06/2020 ∙ by John Bronskill, et al. ∙ 12 ∙ share

read it
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

Modern machine learning methods including deep learning have achieved gr...
06/06/2019 ∙ by Yaniv Ovadia, et al. ∙ 9 ∙ share

read it
From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data

Current face recognition systems robustly recognize identities across a ...
07/20/2018 ∙ by Daniel C. Castro, et al. ∙ 8 ∙ share

read it
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

Making decisions requires information relevant to the task at hand. Many...
09/28/2018 ∙ by Chao Ma, et al. ∙ 6 ∙ share

read it
Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks

Bayesian neural networks (BNNs) hold great promise as a flexible and pri...
10/09/2018 ∙ by Anqi Wu, et al. ∙ 6 ∙ share

read it
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

The goal of this paper is to design image classification systems that, a...
06/18/2019 ∙ by James Requeima, et al. ∙ 6 ∙ share

read it
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks

Variational Bayesian Inference is a popular methodology for approximatin...
02/07/2020 ∙ by Jakub Świątkowski, et al. ∙ 6 ∙ share

read it
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model

In this paper we introduce the ice-start problem, i.e., the challenge of...
08/13/2019 ∙ by Wenbo Gong, et al. ∙ 3 ∙ share

read it
Deep Directional Statistics: Pose Estimation with Uncertainty Quantification

Modern deep learning systems successfully solve many perception tasks su...
05/09/2018 ∙ by Sergey Prokudin, et al. ∙ 2 ∙ share

read it
Adversarially Robust Training through Structured Gradient Regularization

We propose a novel data-dependent structured gradient regularizer to inc...
05/22/2018 ∙ by Kevin Roth, et al. ∙ 2 ∙ share

read it
Occupancy Networks: Learning 3D Reconstruction in Function Space

With the advent of deep neural networks, learning-based approaches for 3...
12/10/2018 ∙ by Lars Mescheder, et al. ∙ 2 ∙ share

read it
Hydra: Preserving Ensemble Diversity for Model Distillation

Ensembles of models have been empirically shown to improve predictive pe...
01/14/2020 ∙ by Linh Tran, et al. ∙ 1 ∙ share

read it
Hybrid VAE: Improving Deep Generative Models using Partial Observations

Deep neural network models trained on large labeled datasets are the sta...
11/30/2017 ∙ by Sergey Tulyakov, et al. ∙ 0 ∙ share

read it
The Atari Grand Challenge Dataset

Recent progress in Reinforcement Learning (RL), fueled by its combinatio...
05/31/2017 ∙ by Vitaly Kurin, et al. ∙ 0 ∙ share

read it
Stabilizing Training of Generative Adversarial Networks through Regularization

Deep generative models based on Generative Adversarial Networks (GANs) h...
05/25/2017 ∙ by Kevin Roth, et al. ∙ 0 ∙ share

read it
Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations

We would like to learn a representation of the data which decomposes an ...
05/24/2017 ∙ by Diane Bouchacourt, et al. ∙ 0 ∙ share

read it
Memory Lens: How Much Memory Does an Agent Use?

We propose a new method to study the internal memory used by reinforceme...
11/21/2016 ∙ by Christoph Dann, et al. ∙ 0 ∙ share

read it
Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring

We present a new notion of probabilistic duality for random variables in...
11/21/2016 ∙ by Lars Mescheder, et al. ∙ 0 ∙ share

read it
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

Generative neural samplers are probabilistic models that implement sampl...
06/02/2016 ∙ by Sebastian Nowozin, et al. ∙ 0 ∙ share

read it
PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning

State-of-the-art computer vision algorithms often achieve efficiency by ...
12/12/2016 ∙ by Alexander Krull, et al. ∙ 0 ∙ share

read it
DSAC - Differentiable RANSAC for Camera Localization

RANSAC is an important algorithm in robust optimization and a central bu...
11/17/2016 ∙ by Eric Brachmann, et al. ∙ 0 ∙ share

read it
DISCO Nets: DISsimilarity COefficient Networks

We present a new type of probabilistic model which we call DISsimilarity...
06/08/2016 ∙ by Diane Bouchacourt, et al. ∙ 0 ∙ share

read it
Bayesian Inference for NMR Spectroscopy with Applications to Chemical Quantification

Nuclear magnetic resonance (NMR) spectroscopy exploits the magnetic prop...
02/14/2014 ∙ by Andrew Gordon Wilson, et al. ∙ 0 ∙ share

read it
Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo

We propose a computational model for shape, illumination and albedo infe...
07/22/2015 ∙ by Amit Adam, et al. ∙ 0 ∙ share

read it
The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision Models

Computer vision is hard because of a large variability in lighting, shap...
02/04/2014 ∙ by Varun Jampani, et al. ∙ 0 ∙ share

read it
Decision-Theoretic Meta-Learning: Versatile and Efficient Amortization of Few-Shot Learning

This paper develops a general framework for data efficient and versatile...
05/24/2018 ∙ by Jonathan Gordon, et al. ∙ 0 ∙ share

read it
Which Training Methods for GANs do actually Converge?

Recent work has shown local convergence of GAN training for absolutely c...
01/13/2018 ∙ by Lars Mescheder, et al. ∙ 0 ∙ share

read it

Sebastian Nowozin

Featured Co-authors