4.6k citations · 9.7k across the 24 of their papers we have counts for
27 papers
A density estimation perspective on learning from pairwise human preferences
Vincent Dumoulin, Daniel D. Johnson, Pablo Samuel Castro +2
Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and…
Active learning for fast and slow modeling attacks on Arbiter PUFs
Vincent Dumoulin, Wenjing Rao, Natasha Devroye
Modeling attacks, in which an adversary uses machine learning techniques to model a hardware-based Physically Unclonable Function (PUF) pose a great threat to the viability of thes…
In Search for a Generalizable Method for Source Free Domain Adaptation
Malik Boudiaf, Tom Denton, Bart van Merriënboer +2
Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data. In this work, we apply existing SFD…
Proper Reuse of Image Classification Features Improves Object Detection
Cristina Vasconcelos, Vighnesh Birodkar, Vincent Dumoulin
A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature…
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
Utku Evci, Vincent Dumoulin, Hugo Larochelle +1
Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing…
Impact of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +3
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limi…
Domain Conditional Predictors for Domain Adaptation
Joao Monteiro, Xavier Gibert, Jianqiao Feng +2
Learning guarantees often rely on assumptions of i.i.d. data, which will likely be violated in practice once predictors are deployed to perform real-world tasks. Domain adaptation…
Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou, Hugo Larochelle, Richard Zemel +1
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purp…
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Vincent Dumoulin, Neil Houlsby, Utku Evci +4
Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art advances in each family are measured large…
An Effective Anti-Aliasing Approach for Residual Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +2
Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning.…
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin +8
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and d…
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar +12
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made…
Cross-Modulation Networks for Few-Shot Learning
Hugo Prol, Vincent Dumoulin, Luis Herranz
A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This c…
Generative Adversarial Networks: An Overview
Antonia Creswell, Tom White, Vincent Dumoulin +3
Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation s…
FiLM: Visual Reasoning with a General Conditioning Layer
Ethan Perez, Florian Strub, Harm de Vries +2
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, f…
Learning Visual Reasoning Without Strong Priors
Ethan Perez, Harm de Vries, Florian Strub +2
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial gener…
Exploring the structure of a real-time, arbitrary neural artistic stylization network
Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur +2
In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time styliz…
Improved Training of Wasserstein GANs
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky +2
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stab…
A Learned Representation For Artistic Style
Vincent Dumoulin, Jonathon Shlens, Manjunath Kudlur
The diversity of painting styles represents a rich visual vocabulary for the construction of an image. The degree to which one may learn and parsimoniously capture this visual voca…
Adversarially Learned Inference
Vincent Dumoulin, Ishmael Belghazi, Ben Poole +4
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation networ…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
A guide to convolution arithmetic for deep learning
Vincent Dumoulin, Francesco Visin
We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various…
Discriminative Regularization for Generative Models
Alex Lamb, Vincent Dumoulin, Aaron Courville
We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to c…
Blocks and Fuel: Frameworks for deep learning
Bart van Merriënboer, Dzmitry Bahdanau, Vincent Dumoulin +4
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitat…