
TaskNorm: Rethinking Batch Normalization for MetaLearning
Modern metalearning approaches for image classification rely on increas...
read it

The ktied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximatin...
read it

How Good is the Bayes Posterior in Deep Neural Networks Really?
During the past five years the Bayesian deep learning community has deve...
read it

Hydra: Preserving Ensemble Diversity for Model Distillation
Ensembles of models have been empirically shown to improve predictive pe...
read it

Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
Recently there has been an increased interest in unsupervised learning o...
read it

Icebreaker: Elementwise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
In this paper we introduce the icestart problem, i.e., the challenge of...
read it

Fast and Flexible MultiTask Classification Using Conditional Neural Adaptive Processes
The goal of this paper is to design image classification systems that, a...
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...
read it

Occupancy Networks: Learning 3D Reconstruction in Function Space
With the advent of deep neural networks, learningbased approaches for 3...
read it

Contextual Face Recognition with a NestedHierarchical Nonparametric Identity Model
Current face recognition systems typically operate via classification in...
read it

Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks
Bayesian neural networks (BNNs) hold great promise as a flexible and pri...
read it

EDDI: Efficient Dynamic Discovery of HighValue Information with Partial VAE
Making decisions requires information relevant to the task at hand. Many...
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 ...
read it

DecisionTheoretic MetaLearning: Versatile and Efficient Amortization of FewShot Learning
This paper develops a general framework for data efficient and versatile...
read it

Adversarially Robust Training through Structured Gradient Regularization
We propose a novel datadependent structured gradient regularizer to inc...
read it

Deep Directional Statistics: Pose Estimation with Uncertainty Quantification
Modern deep learning systems successfully solve many perception tasks su...
read it

Which Training Methods for GANs do actually Converge?
Recent work has shown local convergence of GAN training for absolutely c...
read it

Hybrid VAE: Improving Deep Generative Models using Partial Observations
Deep neural network models trained on large labeled datasets are the sta...
read it

The Atari Grand Challenge Dataset
Recent progress in Reinforcement Learning (RL), fueled by its combinatio...
read it

Stabilizing Training of Generative Adversarial Networks through Regularization
Deep generative models based on Generative Adversarial Networks (GANs) h...
read it

MultiLevel Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
We would like to learn a representation of the data which decomposes an ...
read it

PoseAgent: BudgetConstrained 6D Object Pose Estimation via Reinforcement Learning
Stateoftheart computer vision algorithms often achieve efficiency by ...
read it

Memory Lens: How Much Memory Does an Agent Use?
We propose a new method to study the internal memory used by reinforceme...
read it

Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring
We present a new notion of probabilistic duality for random variables in...
read it

DSAC  Differentiable RANSAC for Camera Localization
RANSAC is an important algorithm in robust optimization and a central bu...
read it

DISCO Nets: DISsimilarity COefficient Networks
We present a new type of probabilistic model which we call DISsimilarity...
read it

fGAN: Training Generative Neural Samplers using Variational Divergence Minimization
Generative neural samplers are probabilistic models that implement sampl...
read it

Bayesian TimeofFlight for Realtime Shape, Illumination and Albedo
We propose a computational model for shape, illumination and albedo infe...
read it

Bayesian Inference for NMR Spectroscopy with Applications to Chemical Quantification
Nuclear magnetic resonance (NMR) spectroscopy exploits the magnetic prop...
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...
read it
Sebastian Nowozin
is this you? claim profile
Principal Researcher at Microsoft Research, Cambridge, UK, managing the Machine Intelligence and Perception group.