papers

Publications (100)

cs.CV2025

A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models

Reda Bensaid, Vincent Gripon, François Leduc-Primeau +3

Few-shot semantic segmentation (FSS) is a crucial challenge in computer vision, driving extensive research into a diverse range of methods, from advanced meta-learning techniques t…

cs.LG2022

Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding

Yassine El Ouahidi, Hugo Tessier, Giulia Lioi +3

Graph Signal Processing is a promising framework to manipulate brain signals as it allows to encompass the spatial dependencies between the activity in regions of interest in the b…

cs.NE2023

ThinResNet: A New Baseline for Structured Convolutional Networks Pruning

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…

cs.NE2019

Attention Based Pruning for Shift Networks

Ghouthi Boukli Hacene, Carlos Lassance, Vincent Gripon +2

In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it is often required to assemble a large…

cs.LG2023

A Statistical Model for Predicting Generalization in Few-Shot Classification

Yassir Bendou, Vincent Gripon, Bastien Pasdeloup +5

The estimation of the generalization error of classifiers often relies on a validation set. Such a set is hardly available in few-shot learning scenarios, a highly disregarded shor…

cs.CV2019

Efficient Hardware Implementation of Incremental Learning and Inference on Chip

Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia +2

In this paper, we tackle the problem of incrementally learning a classifier, one example at a time, directly on chip. To this end, we propose an efficient hardware implementation o…

cs.CV2018

Transfer Incremental Learning using Data Augmentation

Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia +2

Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power. Such methods still remain highly inappr…

cs.NE2022

Leveraging Structured Pruning of Convolutional Neural Networks

Hugo Tessier, Vincent Gripon, Mathieu Léonardon +3

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. However, depending on the a…

cs.AR2013

A Low-Power Content-Addressable-Memory Based on Clustered-Sparse-Networks

Hooman Jarollahi, Vincent Gripon, Naoya Onizawa +1

A low-power Content-Addressable-Memory (CAM) is introduced employing a new mechanism for associativity between the input tags and the corresponding address of the output data. The…

cs.LG2019

Improved Visual Localization via Graph Smoothing

Carlos Lassance, Yasir Latif, Ravi Garg +2

Vision based localization is the problem of inferring the pose of the camera given a single image. One solution to this problem is to learn a deep neural network to infer the pose…

cs.LG2022

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

Yassir Bendou, Yuqing Hu, Raphael Lafargue +4

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 lab…

cs.LG2020

BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization

Miloš Nikolić, Ghouthi Boukli Hacene, Ciaran Bannon +5

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…

cs.LG2019

A Unified Deep Learning Formalism For Processing Graph Signals

Myriam Bontonou, Carlos Lassance, Jean-Charles Vialatte +1

Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images). However, as they can not be used on signals defined o…

cs.NE2013

Improving Sparse Associative Memories by Escaping from Bogus Fixed Points

Zhe Yao, Vincent Gripon, Michael Rabbat

The Gripon-Berrou neural network (GBNN) is a recently invented recurrent neural network embracing a LDPC-like sparse encoding setup which makes it extremely resilient to noise and…

cs.NE2013

Storing non-uniformly distributed messages in networks of neural cliques

Bartosz Boguslawski, Vincent Gripon, Fabrice Seguin +1

Associative memories are data structures that allow retrieval of stored messages from part of their content. They thus behave similarly to human brain that is capable for instance…

cs.NE2022

Rethinking Weight Decay For Efficient Neural Network Pruning

Hugo Tessier, Vincent Gripon, Mathieu Léonardon +3

Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks. Despite many innovations in recent decades, pruning…

cs.NE2020

GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning

Lyes Khacef, Vincent Gripon, Benoit Miramond

Few-shot classification is a challenge in machine learning where the goal is to train a classifier using a very limited number of labeled examples. This scenario is likely to occur…

cs.DC2012

Forwarding Without Repeating: Efficient Rumor Spreading in Bounded-Degree Graphs

Vincent Gripon, Vitaly Skachek, Michael Rabbat

We study a gossip protocol called forwarding without repeating (FWR). The objective is to spread multiple rumors over a graph as efficiently as possible. FWR accomplishes this by h…

cs.AI2026

D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding

Jonathan Lys, Vincent Gripon, Axel Marmoret +4

Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard autoregressive sear…

cs.CV2017

Memory vectors for similarity search in high-dimensional spaces

Ahmet Iscen, Teddy Furon, Vincent Gripon +2

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. This arch…

cs.LG2020

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs

Carlos Lassance, Louis Béthune, Myriam Bontonou +2

Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry…

cs.LG2022

Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings

Aymane Abdali, Vincent Gripon, Lucas Drumetz +1

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 restra…

cs.LG2021

Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification

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. In this context, works have proposed to introduce…

cs.NE2012

Learning sparse messages in networks of neural cliques

Behrooz Kamary Aliabadi, Claude Berrou, Vincent Gripon +1

An extension to a recently introduced binary neural network is proposed in order to allow the learning of sparse messages, in large numbers and with high memory efficiency. This ne…

cs.LG2024

Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning

Raphael Lafargue, Luke Smith, Franck Vermet +4

The predominant method for computing confidence intervals (CI) in few-shot learning (FSL) is based on sampling the tasks with replacement, i.e.\ allowing the same samples to appear…

cs.LG2024

On Transfer in Classification: How Well do Subsets of Classes Generalize?

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…

cs.CV2023

Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning

Yassir Bendou, Vincent Gripon, Bastien Pasdeloup +4

In the realm of few-shot learning, foundation models like CLIP have proven effective but exhibit limitations in cross-domain robustness especially in few-shot settings. Recent work…

cs.LG2020

Some Remarks on Replicated Simulated Annealing

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 statist…

cs.DM2016

Toward An Uncertainty Principle For Weighted Graphs

Bastien Pasdeloup, Réda Alami, Vincent Gripon +1

The uncertainty principle states that a signal cannot be localized both in time and frequency. With the aim of extending this result to signals on graphs, Agaskar&Lu introduce noti…

cs.DS2013

Reconstructing a Graph from Path Traces

Vincent Gripon, Michael Rabbat

This paper considers the problem of inferring the structure of a network from indirect observations. Each observation (a "trace") is the unordered set of nodes which are activated…

cs.LG2026

TensLoRA: Tensor Alternatives for Low-Rank Adaptation

Axel Marmoret, Reda Bensaid, Jonathan Lys +2

Low-Rank Adaptation (LoRA) is widely used to efficiently adapt Transformers by adding trainable low-rank matrices to attention projections. While effective, these matrices are cons…

math.PR2016

A Comparative Study of Sparse Associative Memories

Vincent Gripon, Judith Heusel, Matthias Löwe +1

We study various models of associative memories with sparse information, i.e. a pattern to be stored is a random string of s and s with about s, only. We compare…

cs.OH2016

Towards a characterization of the uncertainty curve for graphs

Bastien Pasdeloup, Vincent Gripon, Grégoire Mercier +1

Signal processing on graphs is a recent research domain that aims at generalizing classical tools in signal processing, in order to analyze signals evolving on complex domains. Suc…

cs.CV2022

Preserving Fine-Grain Feature Information in Classification via Entropic Regularization

Raphael Baena, Lucas Drumetz, Vincent Gripon

Labeling a classification dataset implies to define classes and associated coarse labels, that may approximate a smoother and more complicated ground truth. For example, natural im…

cs.LG2021

Graphs as Tools to Improve Deep Learning Methods

Carlos Lassance, Myriam Bontonou, Mounia Hamidouche +3

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still…

cs.LG2021

Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes

Mathieu Léonardon, Vincent Gripon

Polar codes can theoretically achieve very competitive Frame Error Rates. In practice, their performance may depend on the chosen decoding procedure, as well as other parameters of…

cs.LG2018

Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness

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. As a matter of fact, in sensitive settings misclassification can lead to…

cs.DS2017

Characterization and Inference of Graph Diffusion Processes from Observations of Stationary Signals

Bastien Pasdeloup, Vincent Gripon, Grégoire Mercier +2

Many tools from the field of graph signal processing exploit knowledge of the underlying graph's structure (e.g., as encoded in the Laplacian matrix) to process signals on the grap…

cs.FL2011

Qualitative Concurrent Stochastic Games with Imperfect Information

Vincent Gripon, Olivier Serre

We study a model of games that combines concurrency, imperfect information and stochastic aspects. Those are finite states games in which, at each round, the two players choose, si…

cs.LG2025

Anomalous Samples for Few-Shot Anomaly Detection

Aymane Abdali, Bartosz Boguslawski, Lucas Drumetz +1

Several anomaly detection and classification methods rely on large amounts of non-anomalous or "normal" samples under the assump- tion that anomalous data is typically harder to ac…

cs.CV2024

LLM meets Vision-Language Models for Zero-Shot One-Class Classification

Yassir Bendou, Giulia Lioi, Bastien Pasdeloup +4

We consider the problem of zero-shot one-class visual classification, extending traditional one-class classification to scenarios where only the label of the target class is availa…

eess.SP2019

Comparing linear structure-based and data-driven latent spatial representations for sequence prediction

Myriam Bontonou, Carlos Lassance, Vincent Gripon +1

Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging. Yet it is a highly difficult pro…

eess.SP2022

Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities

Yassine El Ouahidi, Lucas Drumetz, Giulia Lioi +3

BCI Motor Imagery datasets usually are small and have different electrodes setups. When training a Deep Neural Network, one may want to capitalize on all these datasets to increase…

cs.LG2022

Preventing Manifold Intrusion with Locality: Local Mixup

Raphael Baena, Lucas Drumetz, Vincent Gripon

Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to…

cs.LG2021

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-sh…

cs.LG2017

Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs

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. Namely, we use the support of…

cs.IT2016

Graph reconstruction from the observation of diffused signals

Bastien Pasdeloup, Michael Rabbat, Vincent Gripon +2

Signal processing on graphs has received a lot of attention in the recent years. A lot of techniques have arised, inspired by classical signal processing ones, to allow studying si…

cs.CV2026

Contrastive Learning for Seismic Horizon Tracking with Domain-Specific Priors

Alexandre Thouvenot, Lionel Boillot, Vincent Gripon

Unsupervised 3D seismic horizon tracking faces a key limitation: signal-based propagators provide accurate trace-level alignment but often fail near faults, whereas texture-driven…

cs.LG2020

Representing Deep Neural Networks Latent Space Geometries with Graphs

Carlos Lassance, Vincent Gripon, Antonio Ortega

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists…

cs.LG2020

Predicting the Accuracy of a Few-Shot Classifier

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. In thi…

cs.LG2018

Matching Convolutional Neural Networks without Priors about Data

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. Our method matches the acc…

cs.NE2017

Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise

Eliott Coyac, Vincent Gripon, Charlotte Langlais +1

The brain is a noisy system subject to energy constraints. These facts are rarely taken into account when modelling artificial neural networks. In this paper, we are interested in…

cs.LG2019

Introducing Graph Smoothness Loss for Training Deep Learning Architectures

Myriam Bontonou, Carlos Lassance, Ghouthi Boukli Hacene +3

We introduce a novel loss function for training deep learning architectures to perform classification. It consists in minimizing the smoothness of label signals on similarity graph…

cs.SD2026

MUKA: Multi Kernel Audio Adaptation Of Audio-Language Models

Reda Bensaid, Amine Ouasfi, Yassir Bendou +4

Multimodal foundation models have demonstrated impressive generalization capabilities, yet efficiently adapting them to new tasks in a few-shot setting remains a critical challenge…

cs.NE2013

A study of retrieval algorithms of sparse messages in networks of neural cliques

Ala Aboudib, Vincent Gripon, Xiaoran Jiang

Associative memories are data structures addressed using part of the content rather than an index. They offer good fault reliability and biological plausibility. Among different fa…

cs.AI2013

A Massively Parallel Associative Memory Based on Sparse Neural Networks

Zhe Yao, Vincent Gripon, Michael G. Rabbat

Associative memories store content in such a way that the content can be later retrieved by presenting the memory with a small portion of the content, rather than presenting the me…

cs.LG2020

Graph topology inference benchmarks for machine learning

Carlos Lassance, Vincent Gripon, Gonzalo Mateos

Graphs are nowadays ubiquitous in the fields of signal processing and machine learning. As a tool used to express relationships between objects, graphs can be deployed to various e…

cs.LG2018

Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks

Ghouthi Boukli Hacene, Vincent Gripon, Matthieu Arzel +2

Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters the…

cs.CV2017

Evaluating Graph Signal Processing for Neuroimaging Through Classification and Dimensionality Reduction

Mathilde Ménoret, Nicolas Farrugia, Bastien Pasdeloup +1

Graph Signal Processing (GSP) is a promising framework to analyze multi-dimensional neuroimaging datasets, while taking into account both the spatial and functional dependencies be…

cs.LG2021

Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common…

cs.LG2021

Few-shot Decoding of Brain Activation Maps

Myriam Bontonou, Giulia Lioi, Nicolas Farrugia +1

Few-shot learning addresses problems for which a limited number of training examples are available. So far, the field has been mostly driven by applications in computer vision. Her…

stat.ML2021

Improving Classification Accuracy with Graph Filtering

Mounia Hamidouche, Carlos Lassance, Yuqing Hu +3

In machine learning, classifiers are typically susceptible to noise in the training data. In this work, we aim at reducing intra-class noise with the help of graph filtering to imp…

cs.CV2025

Object-Centric Cropping for Visual Few-Shot Classification

Aymane Abdali, Bartosz Boguslawski, Lucas Drumetz +1

In the domain of Few-Shot Image Classification, operating with as little as one example per class, the presence of image ambiguities stemming from multiple objects or complex backg…

eess.SP2021

Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks

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. Among these tools are translations, whi…

q-bio.NC2017

SimiNet: a Novel Method for Quantifying Brain Network Similarity

Ahmad Mheich, Mahmoud Hassan, Mohamad Khalil +3

Quantifying the similarity between two networks is critical in many applications. A number of algorithms have been proposed to compute graph similarity, mainly based on the propert…

cs.NE2014

Combating Corrupt Messages in Sparse Clustered Associative Memories

Zhe Yao, Vincent Gripon, Michael Rabbat

In this paper we analyze and extend the neural network based associative memory proposed by Gripon and Berrou. This associative memory resembles the celebrated Willshaw model with…

eess.SP2024

Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding

Yassine El Ouahidi, Giulia Lioi, Nicolas Farrugia +2

In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches offline performance level while being usable online without requiring supervision. Interesti…

cs.LG2020

DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems

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. Indeed, Deep Neural Networks are now the golden standard…

cs.DM2016

Neighborhood-Preserving Translations on Graphs

Nicolas Grelier, Bastien Pasdeloup, Jean-Charles Vialatte +1

In many domains (e.g. Internet of Things, neuroimaging) signals are naturally supported on graphs. These graphs usually convey information on similarity between the values taken by…

cs.CV2025

ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models

Yassir Bendou, Amine Ouasfi, Vincent Gripon +1

The growing popularity of Contrastive Language-Image Pretraining (CLIP) has led to its widespread application in various visual downstream tasks. To enhance CLIP's effectiveness an…

cs.LG2019

Training Modern Deep Neural Networks for Memory-Fault Robustness

Ghouthi Boukli Hacene, François Leduc-Primeau, Amal Ben Soussia +2

Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging. In this paper, we inve…

cs.LG2019

Structural Robustness for Deep Learning Architectures

Carlos Lassance, Vincent Gripon, Jian Tang +1

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including…

cs.CV2026

SLAD : Shared LoRA Adapters for Task Specific Distillation

Reda Bensaid, Yassir Bendou, Vincent Gripon +1

In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has…

eess.SP2024

A Strong and Simple Deep Learning Baseline for BCI MI Decoding

Yassine El Ouahidi, Vincent Gripon, Bastien Pasdeloup +3

We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline t…

cs.LG2019

Deep geometric knowledge distillation with graphs

Carlos Lassance, Myriam Bontonou, Ghouthi Boukli Hacene +3

In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resour…

cs.LG2017

Generalizing the Convolution Operator to extend CNNs to Irregular Domains

Jean-Charles Vialatte, Vincent Gripon, Grégoire Mercier

Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks. Their convolutional filters are of paramount importance for they allow to…

cs.DM2018

Convolutional neural networks on irregular domains based on approximate vertex-domain translations

Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte +2

We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such a…

cs.LG2026

Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training

Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4

Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contri…

cs.LG2022

Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification

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…

cs.CL2026

Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers

Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignme…

cs.LG2020

ThriftyNets : Convolutional Neural Networks with Tiny Parameter Budget

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 down…

cs.LG2021

Quantization and Deployment of Deep Neural Networks on Microcontrollers

Pierre-Emmanuel Novac, Ghouthi Boukli Hacene, Alain Pegatoquet +2

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design. Presently…

cs.CV2020

Towards an Intrinsic Definition of Robustness for a Classifier

Théo Giraudon, Vincent Gripon, Matthias Löwe +1

The robustness of classifiers has become a question of paramount importance in the past few years. Indeed, it has been shown that state-of-the-art deep learning architectures can e…

cs.LG2019

Transfer Learning with Sparse Associative Memories

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. Based on Associative Memories, this lay…

cs.LG2016

Compression of Deep Neural Networks on the Fly

Guillaume Soulié, Vincent Gripon, Maëlys Robert

Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be tra…

cs.NE2014

Storing sequences in binary tournament-based neural networks

Xiaoran Jiang, Vincent Gripon, Claude Berrou +1

An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high efficiency. To obtain…

cs.LG2021

Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification

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. These conditions are likely to cause underdete…

cs.NE2022

Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU

Hugo Tessier, Vincent Gripon, Mathieu Léonardon +3

Deep neural networks are the state of the art in many computer vision tasks. Their deployment in the context of autonomous vehicles is of particular interest, since their limitatio…

cs.LG2025

Input Resolution Downsizing as a Compression Technique for Vision Deep Learning Systems

Jeremy Morlier, Mathieu Leonardon, Vincent Gripon

Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous…

cs.CV2024

Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes

Raphael Lafargue, Yassir Bendou, Bastien Pasdeloup +4

When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``targe…

cs.IT2013

Maximum Likelihood Associative Memories

Vincent Gripon, Michael Rabbat

Associative memories are structures that store data in such a way that it can later be retrieved given only a part of its content -- a sort-of error/erasure-resilience property. Th…

cs.LG2017

Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation

Vincent Gripon, Ghouthi B. Hacene, Matthias Löwe +1

Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years. It allows to obtain state-of-the-art accuracy on dataset…

eess.SP2020

Gradients of Connectivity as Graph Fourier Bases of Brain Activity

Giulia Lioi, Vincent Gripon, Abdelbasset Brahim +2

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 neu…

cs.LG2017

Associative Memories to Accelerate Approximate Nearest Neighbor Search

Vincent Gripon, Matthias Löwe, Franck Vermet

Nearest neighbor search is a very active field in machine learning for it appears in many application cases, including classification and object retrieval. In its canonical version…

cs.LG2026

MONET: Modeling and Optimization of neural NEtwork Training from Edge to Data Centers

Jérémy Morlier, Robin Geens, Stef Cuyckens +4

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge.…

cs.CV2023

Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach

Yassir Bendou, Lucas Drumetz, Vincent Gripon +2

The field of visual few-shot classification aims at transferring the state-of-the-art performance of deep learning visual systems onto tasks where only a very limited number of tra…

cs.DM2018

A neighborhood-preserving translation operator on graphs

Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte +2

In this paper, we introduce translation operators on graphs. Contrary to spectrally-defined translations in the framework of graph signal processing, our operators mimic neighborho…

cs.LG2011

Sparse neural networks with large learning diversity

Vincent Gripon, Claude Berrou

Coded recurrent neural networks with three levels of sparsity are introduced. The first level is related to the size of messages, much smaller than the number of available neurons.…

cs.LG2025

REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects

Yassine El Ouahidi, Jonathan Lys, Philipp Thölke +5

Foundation models have transformed AI by reducing reliance on task-specific data through large-scale pretraining. While successful in language and vision, their adoption in EEG has…

cs.CV2026

Efficient Few-Shot Learning for Edge AI via Knowledge Distillation on MobileViT

Shuhei Tsuyuki, Reda Bensaid, Jérémy Morlier +4

Efficient and adaptable deep learning models are an important area of deep learning research, driven by the need for highly efficient models on edge devices. Few-shot learning enab…