AIConfPaper
← Search

Sebastian Nowozin

33 accepted papers

2023

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

Aliaksandra Shysheya, John F Bronskill, Massimiliano Patacchiola, Sebastian Nowozin, Richard E Turner
ICLR 2023poster

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training protocols. In this work, we develop FiLM Transfer (FiT) whic…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗
2023

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde, Bruno Kacper Mlodozeniec, Marc Brockschmidt, Sebastian Nowozin +2
NeurIPS 2023spotlight

*Molecular dynamics* (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{s}$). MD is often used to compute equilibrium p…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2022

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

Massimiliano Patacchiola, John F Bronskill, Aliaksandra Shysheya, Katja Hofmann, Sebastian Nowozin, Richard E Turner
NeurIPS 2022accept

Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a pretrained system is adapted by learning on small amounts of labeled data belonging to a specific user. This setting requ…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2021

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect

Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann
NeurIPS 2021poster

The “cold posterior effect” (CPE) in Bayesian deep learning describes the disturbing observation that the predictive performance of Bayesian neural networks can be significantly improved if the Bayes posterior is artificially sharpened using a temperature parameter T <1. The CPE is problematic in t…

Cited by 27Source ↗PDF ↗Scholar ↗
2021

Memory Efficient Meta-Learning with Large Images

John F Bronskill, Daniela Massiceti, Massimiliano Patacchiola, Katja Hofmann, Sebastian Nowozin, Richard E Turner
NeurIPS 2021poster

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This limitation arises because a task's entire support set, which can…

Cited by 26Source ↗PDF ↗Scholar ↗
2021

Precise characterization of the prior predictive distribution of deep ReLU networks

Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann
NeurIPS 2021spotlight

Recent works on Bayesian neural networks (BNNs) have highlighted the need to better understand the implications of using Gaussian priors in combination with the compositional structure of the network architecture. Similar in spirit to the kind of analysis that has been developed to devise better in…

Cited by 39Source ↗PDF ↗Scholar ↗
2020

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

Florian Wenzel, Kevin Roth, Bastiaan Veeling, Jakub Swiatkowski, Linh Tran, Stephan Mandt +4
ICML 2020poster

During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference in deep neural networks. However, despite this algorithmic progress and the promise of improved uncertainty quantificat…

Cited by 451Source ↗PDF ↗code ↗Scholar ↗
2020

Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations

Jan Stuehmer, Richard Turner, Sebastian Nowozin
AISTATS 2020poster

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost function to achieve this goal. We first show that these modificati…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2020

TaskNorm: Rethinking Batch Normalization for Meta-Learning

John Bronskill, Jonathan Gordon, James Requeima, Sebastian Nowozin, Richard Turner
ICML 2020poster

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical nature of the meta-learning setting presents several challenges…

Cited by 122Source ↗PDF ↗code ↗Scholar ↗
2020

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

Jakub Swiatkowski, Kevin Roth, Bastiaan Veeling, Linh Tran, Joshua Dillon, Jasper Snoek +4
ICML 2020poster

Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods has explored ever richer parameterizations of the approximate posterior in the hope of improving performance. In contra…

Cited by 71Source ↗PDF ↗Scholar ↗
2019

Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D. Sculley, Sebastian Nowozin +3
NeurIPS 2019poster

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive uncertainty. Quantifying uncertainty is especially critical in real-world settings, which…

Cited by 2106Source ↗PDF ↗code ↗Scholar ↗
2019

Deterministic Variational Inference for Robust Bayesian Neural Networks

Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt
ICLR 2019oral

Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes (VB) is theoretically grounded, generally applicable, and c…

Cited by 248Source ↗PDF ↗code ↗Scholar ↗
2019

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

Chao Ma, Sebastian Tschiatschek, Konstantina Palla, Jose Miguel Hernandez-Lobato, Sebastian Nowozin, Cheng Zhang
ICML 2019oral

Many real-life decision making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may decide to take additional measurements such as diagnostic tests or imaging scans before making a final assessment. Acquiring…

Cited by 163Source ↗PDF ↗code ↗Scholar ↗
2019

Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes

James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, Richard E Turner
NeurIPS 2019spotlight

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and es…

Cited by 312Source ↗PDF ↗code ↗Scholar ↗
2019

Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model

Wenbo Gong, Sebastian Tschiatschek, Sebastian Nowozin, Richard E Turner, José Miguel Hernández-Lobato, Cheng Zhang
NeurIPS 2019poster

In this paper, we address the ice-start problem, i.e., the challenge of deploying machine learning models when only a little or no training data is initially available, and acquiring each feature element of data is associated with costs. This setting is representative of the real-world machine learn…

Cited by 59Source ↗PDF ↗code ↗Scholar ↗
2019

Meta-Learning Probabilistic Inference for Prediction

Jonathan Gordon, John Bronskill, Matthias Bauer, Sebastian Nowozin, Richard Turner
ICLR 2019poster

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class…

Cited by 330Source ↗PDF ↗code ↗Scholar ↗
2019

Occupancy Networks: Learning 3D Reconstruction in Function Space

Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, Andreas Geiger
CVPR 2019oral

With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary…

Cited by 3382PDF ↗code ↗Scholar ↗
2018

Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational Inference

Sebastian Nowozin
ICLR 2018poster

The importance-weighted autoencoder (IWAE) approach of Burda et al. defines a sequence of increasingly tighter bounds on the marginal likelihood of latent variable models. Recently, Cremer et al. reinterpreted the IWAE bounds as ordinary variational evidence lower bounds (ELBO) applied to increasing…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗
2018

Deep Directional Statistics: Pose Estimation with Uncertainty Quantification

Sergey Prokudin, Peter Gehler, Sebastian Nowozin
ECCV 2018poster

Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging conditions such as on low resolution images or when the image is corrupted by imaging artifacts, current systems degrade consi…

Cited by 121Source ↗PDF ↗code ↗Scholar ↗
2018

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

Daniel Coelho de Castro, Sebastian Nowozin
ECCV 2018poster

Current face recognition systems robustly recognize identities across a wide variety of imaging conditions. In these systems recognition is performed via classification into known identities obtained from supervised identity annotations. There are two problems with this current paradigm: (1) current…

Cited by 10Source ↗PDF ↗Scholar ↗
2018

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples

Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman
ICLR 2018poster

Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show empirically that adversarial examples mainly lie in the low pro…

Cited by 1019Source ↗PDF ↗code ↗Scholar ↗
2017

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

Lars Mescheder, Sebastian Nowozin, Andreas Geiger
ICML 2017poster

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes…

Cited by 679Source ↗PDF ↗Scholar ↗
2017

DSAC - Differentiable RANSAC for Camera Localization

Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold +1
CVPR 2017oral

RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far n…

Cited by 737PDF ↗code ↗Scholar ↗
2017

DeepCoder: Learning to Write Programs

Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow
ICLR 2017poster

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network's predictions to a…

Cited by 752Source ↗Scholar ↗
2017

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

Alexander Krull, Eric Brachmann, Sebastian Nowozin, Frank Michel, Jamie Shotton, Carsten Rother
CVPR 2017poster

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are non-differentiable. As a result, these algorithms are hard t…

Cited by 60PDF ↗Scholar ↗
2017

Stabilizing Training of Generative Adversarial Networks through Regularization

Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann
NeurIPS 2017poster

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch…

Cited by 554Source ↗PDF ↗code ↗Scholar ↗
2016

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

Sebastian Nowozin, Botond Cseke, Ryota Tomioka
NeurIPS 2016poster

Generative neural networks are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples a…

Cited by 2103Source ↗PDF ↗code ↗Scholar ↗
2015

Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations

Jan Stuhmer, Sebastian Nowozin, Andrew Fitzgibbon, Richard Szeliski, Travis Perry, Sunil Acharya +2
ICCV 2015poster

Consumer depth cameras have dramatically improved our ability to track rigid, articulated, and deformable 3D objects in real-time. However, depth cameras have a limited temporal resolution (frame-rate) that restricts the accuracy and robustness of tracking, especially for fast or unpredictable motio…

Cited by 23PDF ↗Scholar ↗