no code implementations • 31 Mar 2024 • Yassir Bendou, Giulia Lioi, Bastien Pasdeloup, Lukas Mauch, Ghouthi Boukli Hacene, Fabien Cardinaux, Vincent Gripon
In this setting, only the label of the target class is available, and the goal is to discriminate between positive and negative query samples without requiring any validation example from the target task.
no code implementations • 15 Mar 2024 • Yassine El Ouahidi, Giulia Lioi, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon
In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches offline performance level while being usable online without requiring supervision.
no code implementations • 6 Mar 2024 • Raphael Baena, Lucas Drumetz, Vincent Gripon
In classification, it is usual to observe that models trained on a given set of classes can generalize to previously unseen ones, suggesting the ability to learn beyond the initial task.
no code implementations • 29 Jan 2024 • Raphael Lafargue, Yassir Bendou, Bastien Pasdeloup, Jean-Philippe Diguet, Ian Reid, Vincent Gripon, Jack Valmadre
Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples.
1 code implementation • 20 Jan 2024 • Reda Bensaid, Vincent Gripon, François Leduc-Primeau, Lukas Mauch, Ghouthi Boukli Hacene, Fabien Cardinaux
In recent years, the rapid evolution of computer vision has seen the emergence of various foundation models, each tailored to specific data types and tasks.
1 code implementation • 24 Nov 2023 • Yassir Bendou, Vincent Gripon, Bastien Pasdeloup, Giulia Lioi, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene
In this paper, we present a novel approach that leverages text-derived statistics to predict the mean and covariance of the visual feature distribution for each class.
1 code implementation • 22 Sep 2023 • Hugo Tessier, Ghouti Boukli Hacene, Vincent Gripon
Pruning is a compression method which aims to improve the efficiency of neural networks by reducing their number of parameters while maintaining a good performance, thus enhancing the performance-to-cost ratio in nontrivial ways.
1 code implementation • 11 Sep 2023 • Yassine El Ouahidi, Vincent Gripon, Bastien Pasdeloup, Ghaith Bouallegue, Nicolas Farrugia, Giulia Lioi
We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI.
1 code implementation • 16 Jan 2023 • Yassir Bendou, Lucas Drumetz, Vincent Gripon, Giulia Lioi, Bastien Pasdeloup
Then, we introduce a downstream classifier meant to exploit the presence of multiple objects to improve the performance of few-shot classification, in the case of extreme settings where only one shot is given for its class.
1 code implementation • 13 Dec 2022 • Yassir Bendou, Vincent Gripon, Bastien Pasdeloup, Lukas Mauch, Stefan Uhlich, Fabien Cardinaux, Ghouthi Boukli Hacene, Javier Alonso Garcia
Such a set is hardly available in few-shot learning scenarios, a highly disregarded shortcoming in the field.
no code implementations • 28 Oct 2022 • Yassine El Ouahidi, Lucas Drumetz, Giulia Lioi, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon
BCI Motor Imagery datasets usually are small and have different electrodes setups.
no code implementations • 23 Sep 2022 • Aymane Abdali, Vincent Gripon, Lucas Drumetz, Bartosz Boguslawski
We consider a novel formulation of the problem of Active Few-Shot Classification (AFSC) where the objective is to classify a small, initially unlabeled, dataset given a very restrained labeling budget.
no code implementations • 18 Sep 2022 • Yuqing Hu, Stéphane Pateux, Vincent Gripon
Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot.
1 code implementation • 7 Aug 2022 • Raphael Baena, Lucas Drumetz, Vincent Gripon
In this paper we are interested in the problem of solving fine-grain classification or regression, using a model trained on coarse-grain labels only.
1 code implementation • 13 Jun 2022 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, David Bertrand, Thomas Hannagan
Deep neural networks are the state of the art in many computer vision tasks.
1 code implementation • 13 Jun 2022 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, David Bertrand, Thomas Hannagan
Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks.
no code implementations • 9 Mar 2022 • Yassine El Ouahidi, Hugo Tessier, Giulia Lioi, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon
In this work, we are interested in better understanding what are the graph frequencies that are the most useful to decode fMRI signals.
3 code implementations • 24 Jan 2022 • Yassir Bendou, Yuqing Hu, Raphael Lafargue, Giulia Lioi, Bastien Pasdeloup, Stéphane Pateux, Vincent Gripon
Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available.
Ranked #1 on Few-Shot Learning on Mini-Imagenet 5-way (1-shot)
1 code implementation • 12 Jan 2022 • Raphael Baena, Lucas Drumetz, Vincent Gripon
Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs.
Ranked #9 on Image Classification on Fashion-MNIST
1 code implementation • 18 Oct 2021 • Yuqing Hu, Vincent Gripon, Stéphane Pateux
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
no code implementations • 8 Oct 2021 • Carlos Lassance, Myriam Bontonou, Mounia Hamidouche, Bastien Pasdeloup, Lucas Drumetz, Vincent Gripon
This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process.
1 code implementation • 23 Aug 2021 • Myriam Bontonou, Nicolas Farrugia, Vincent Gripon
It is very common to face classification problems where the number of available labeled samples is small compared to their dimension.
1 code implementation • 27 May 2021 • Pierre-Emmanuel Novac, Ghouthi Boukli Hacene, Alain Pegatoquet, Benoît Miramond, Vincent Gripon
The quantization methods, relevant in the context of an embedded execution onto a microcontroller, are first outlined.
1 code implementation • 11 May 2021 • Mathieu Léonardon, Vincent Gripon
Polar codes can theoretically achieve very competitive Frame Error Rates.
no code implementations • 18 Feb 2021 • Raphael Baena, Lucas Drumetz, Vincent Gripon
The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs.
no code implementations • 12 Jan 2021 • Mounia Hamidouche, Carlos Lassance, Yuqing Hu, Lucas Drumetz, Bastien Pasdeloup, Vincent Gripon
In machine learning, classifiers are typically susceptible to noise in the training data.
no code implementations • 2 Dec 2020 • Vincent Gripon, Carlos Lassance, Ghouthi Boukli Hacene
Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years.
1 code implementation • 25 Nov 2020 • Carlos Lassance, Louis Béthune, Myriam Bontonou, Mounia Hamidouche, Vincent Gripon
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task.
1 code implementation • 20 Nov 2020 • Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, Thomas Hannagan, David Bertrand
Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks.
no code implementations • 14 Nov 2020 • Carlos Lassance, Vincent Gripon, Antonio Ortega
However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought.
1 code implementation • 23 Oct 2020 • Myriam Bontonou, Giulia Lioi, Nicolas Farrugia, Vincent Gripon
Few-shot learning addresses problems for which a limited number of training examples are available.
no code implementations • 30 Sep 2020 • Vincent Gripon, Matthias Löwe, Franck Vermet
Recently authors have introduced the idea of training discrete weights neural networks using a mix between classical simulated annealing and a replica ansatz known from the statistical physics literature.
no code implementations • 26 Sep 2020 • Giulia Lioi, Vincent Gripon, Abdelbasset Brahim, François Rousseau, Nicolas Farrugia
The application of graph theory to model the complex structure and function of the brain has shed new light on its organization and function, prompting the emergence of network neuroscience.
1 code implementation • 4 Sep 2020 • Lyes Khacef, Vincent Gripon, Benoit Miramond
In this work, we consider the problem of post-labeled few-shot unsupervised learning, a classification task where representations are learned in an unsupervised fashion, to be later labeled using very few annotated examples.
no code implementations • 20 Jul 2020 • Guillaume Coiffier, Ghouthi Boukli Hacene, Vincent Gripon
Typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations.
1 code implementation • 16 Jul 2020 • Carlos Lassance, Vincent Gripon, Gonzalo Mateos
Graphs are nowadays ubiquitous in the fields of signal processing and machine learning.
1 code implementation • 8 Jul 2020 • Myriam Bontonou, Louis Béthune, Vincent Gripon
In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples.
no code implementations • 9 Jun 2020 • Théo Giraudon, Vincent Gripon, Matthias Löwe, Franck Vermet
The robustness of classifiers has become a question of paramount importance in the past few years.
6 code implementations • 6 Jun 2020 • Yuqing Hu, Vincent Gripon, Stéphane Pateux
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
no code implementations • 8 Feb 2020 • Miloš Nikolić, Ghouthi Boukli Hacene, Ciaran Bannon, Alberto Delmas Lascorz, Matthieu Courbariaux, Yoshua Bengio, Vincent Gripon, Andreas Moshovos
Neural networks have demonstrably achieved state-of-the art accuracy using low-bitlength integer quantization, yielding both execution time and energy benefits on existing hardware designs that support short bitlengths.
1 code implementation • 27 Jan 2020 • Yuqing Hu, Vincent Gripon, Stéphane Pateux
In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples.
no code implementations • 23 Nov 2019 • Ghouthi Boukli Hacene, François Leduc-Primeau, Amal Ben Soussia, Vincent Gripon, François Gagnon
Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging.
no code implementations • 18 Nov 2019 • Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia, Matthieu Arzel, Michel Jezequel
In this paper, we tackle the problem of incrementally learning a classifier, one example at a time, directly on chip.
1 code implementation • 8 Nov 2019 • Carlos Lassance, Myriam Bontonou, Ghouthi Boukli Hacene, Vincent Gripon, Jian Tang, Antonio Ortega
Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.
no code implementations • 7 Nov 2019 • Carlos Lassance, Yasir Latif, Ravi Garg, Vincent Gripon, Ian Reid
One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with known poses.
no code implementations • 11 Sep 2019 • Carlos Lassance, Vincent Gripon, Jian Tang, Antonio Ortega
Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.
no code implementations • 19 Aug 2019 • Myriam Bontonou, Carlos Lassance, Vincent Gripon, Nicolas Farrugia
Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging.
1 code implementation • 29 May 2019 • Ghouthi Boukli Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio
In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods.
no code implementations • ICLR 2019 • Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
no code implementations • 1 May 2019 • Myriam Bontonou, Carlos Lassance, Ghouthi Boukli Hacene, Vincent Gripon, Jian Tang, Antonio Ortega
We introduce a novel loss function for training deep learning architectures to perform classification.
no code implementations • 1 May 2019 • Myriam Bontonou, Carlos Lassance, Jean-Charles Vialatte, Vincent Gripon
Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images).
no code implementations • 4 Apr 2019 • Quentin Jodelet, Vincent Gripon, Masafumi Hagiwara
In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification.
no code implementations • 29 Dec 2018 • Ghouthi Boukli Hacene, Vincent Gripon, Matthieu Arzel, Nicolas Farrugia, Yoshua Bengio
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection.
no code implementations • 4 Oct 2018 • Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia, Matthieu Arzel, Michel Jezequel
Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power.
no code implementations • 24 May 2018 • Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
1 code implementation • 27 Feb 2018 • Carlos Eduardo Rosar Kos Lassance, Jean-Charles Vialatte, Vincent Gripon
We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs.
no code implementations • 27 Oct 2017 • Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte, Dominique Pastor, Pascal Frossard
We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure.
no code implementations • 24 Oct 2017 • Vincent Gripon, Ghouthi B. Hacene, Matthias Löwe, Franck Vermet
Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years.
no code implementations • 25 Sep 2017 • Eliott Coyac, Vincent Gripon, Charlotte Langlais, Claude Berrou
In this paper, we are interested in demonstrating that those factors can actually lead to the appearance of robust associative memories.
no code implementations • 8 Jun 2017 • Jean-Charles Vialatte, Vincent Gripon, Gilles Coppin
We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph.
no code implementations • 6 Mar 2017 • Mathilde Ménoret, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon
Graph Signal Processing (GSP) is a promising framework to analyze multi-dimensional neuroimaging datasets, while taking into account both the spatial and functional dependencies between brain signals.
no code implementations • 10 Nov 2016 • Vincent Gripon, Matthias Löwe, Franck Vermet
In its canonical version, the complexity of the search is linear with both the dimension and the cardinal of the collection of vectors the search is performed in.
no code implementations • 3 Jun 2016 • Jean-Charles Vialatte, Vincent Gripon, Grégoire Mercier
Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks.
no code implementations • 29 Sep 2015 • Guillaume Soulié, Vincent Gripon, Maëlys Robert
In this paper we introduce a novel compression method for deep neural networks that is performed during the learning phase.
no code implementations • 10 Dec 2014 • Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou
We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory.
no code implementations • 27 Sep 2014 • Zhe Yao, Vincent Gripon, Michael Rabbat
In this paper we analyze and extend the neural network based associative memory proposed by Gripon and Berrou.
no code implementations • 1 Sep 2014 • Xiaoran Jiang, Vincent Gripon, Claude Berrou, Michael Rabbat
An extension to a recently introduced architecture of clique-based neural networks is presented.
no code implementations • 27 Aug 2013 • Zhe Yao, Vincent Gripon, Michael Rabbat
The latter outperforms the former in terms of retrieval rate by a huge margin.
no code implementations • 21 Aug 2013 • Ala Aboudib, Vincent Gripon, Xiaoran Jiang
We introduce several families of algorithms to enhance the retrieval process performance in recently proposed sparse associative memories based on binary neural networks.
no code implementations • 24 Jul 2013 • Bartosz Boguslawski, Vincent Gripon, Fabrice Seguin, Frédéric Heitzmann
Associative memories are data structures that allow retrieval of stored messages from part of their content.
no code implementations • 28 Mar 2013 • Zhe Yao, Vincent Gripon, Michael G. Rabbat
In this paper we implement a variation of the Gripon-Berrou associative memory on a general purpose graphical processing unit (GPU).