2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Institut national de recherche en sciences et technologies du numériqueFR22 papers
- Centre National de la Recherche ScientifiqueFR13 papers
- Laboratoire Jean KuntzmannFR11 papers
- Centre Inria de l'Université Grenoble AlpesFR9 papers
- Institut polytechnique de GrenobleFR9 papers
- Université Grenoble AlpesFR9 papers
- Meta (United States)US6 papers
- Carnegie Mellon UniversityUS2 papers
- CEA Paris-Saclay - Etablissement de SaclayFR2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- École Normale Supérieure - PSLFR2 papers
- Max Planck Institute for InformaticsDE2 papers
56 papers
Beyond spectral gap (extended): The role of the topology in decentralized learning
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model: more accurate gradients allow them to use larger learning rat…
Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
Jules BOURCIER, Thomas Floquet, Gohar Dashyan +3
In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational…
Expression-preserving face frontalization improves visually assisted speech processing
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud +1
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preser…
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration
Théo Bodrito, Alexandre Zouaoui, Jocelyn Chanussot +1
Hyperspectral imaging offers new perspectives for diverse applications, ranging from the monitoring of the environment using airborne or satellite remote sensing, precision farming…
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
Bruno Lecouat, Jean Ponce, Julien Mairal
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems, and wh…
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont +1
We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range depend…
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Mathilde Caron, Ishan Misra, Julien Mairal +3
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contr…
Beyond the Camera: Neural Networks in World Coordinates
Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid +1
Eye movement and strategic placement of the visual field onto the retina, gives animals increased resolution of the scene and suppresses distracting information. This fundamental s…
Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
Nikita Dvornik, Cordelia Schmid, Julien Mairal
Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new…
Convolutional Kernel Networks for Graph-Structured Data
Dexiong Chen, Laurent Jacob, Julien Mairal
We introduce a family of multilayer graph kernels and establish new links between graph convolutional neural networks and kernel methods. Our approach generalizes convolutional ker…
Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions
Grégoire Mialon, Alexandre d'Aspremont, Julien Mairal
We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees. We derive loss functions that produce…
Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
Bruno Lecouat, Jean Ponce, Julien Mairal
Non-local self-similarity and sparsity principles have proven to be powerful priors for natural image modeling. We propose a novel differentiable relaxation of joint sparsity that…
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Alexandre Sablayrolles, Matthijs Douze, Yann Ollivier +2
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the op…
Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image
Roman Klokov, Jakob Verbeek, Edmond Boyer
We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that expl…
Recurrent Kernel Networks
Dexiong Chen, Laurent Jacob, Julien Mairal
Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end train…
A Generic Acceleration Framework for Stochastic Composite Optimization
Andrei Kulunchakov, Julien Mairal
In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex. Specif…
Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
Andrei Kulunchakov, Julien Mairal
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Neste…
Adaptive Density Estimation for Generative Models
Thomas Lucas, Konstantin Shmelkov, Karteek Alahari +2
Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, an…
Modulated Policy Hierarchies
Alexander Pashevich, Danijar Hafner, James Davidson +2
Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often req…
Understanding Priors in Bayesian Neural Networks at the Unit Level
Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo +1
We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to in…
A Kernel Perspective for Regularizing Deep Neural Networks
Alberto Bietti, Grégoire Mialon, Dexiong Chen +1
We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS). Even though this norm cannot be computed, it ad…
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Maha Elbayad, Laurent Besacier, Jakob Verbeek
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on…
Modeling Spatio-Temporal Human Track Structure for Action Localization
Guilhem Chéron, Anton Osokin, Ivan Laptev +1
This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to…
Mixed batches and symmetric discriminators for GAN training
Thomas Lucas, Corentin Tallec, Jakob Verbeek +1
Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminato…