Search Results for author:
Found 71 papers, 26 papers with code
Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
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)
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples.
A Strong and Simple Deep Learning Baseline for BCI MI Decoding
We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI.
GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning
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.
Deep geometric knowledge distillation with graphs
Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.
Few-shot Decoding of Brain Activation Maps
Few-shot learning addresses problems for which a limited number of training examples are available.
Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples.
Graph topology inference benchmarks for machine learning
Graphs are nowadays ubiquitous in the fields of signal processing and machine learning.
Matching Convolutional Neural Networks without Priors about Data
We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs.
Attention Based Pruning for Shift Networks
In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods.
Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task.
Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes
Polar codes can theoretically achieve very competitive Frame Error Rates.
A Statistical Model for Predicting Generalization in Few-Shot Classification
Such a set is hardly available in few-shot learning scenarios, a highly disregarded shortcoming in the field.
Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
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.
Predicting the Accuracy of a Few-Shot Classifier
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.
Rethinking Weight Decay For Efficient Neural Network Pruning
Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks.
Preventing Manifold Intrusion with Locality: Local Mixup
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
A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models
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.
Energy Consumption Analysis of pruned Semantic Segmentation Networks on an Embedded GPU
Deep neural networks are the state of the art in many computer vision tasks.
Leveraging Structured Pruning of Convolutional Neural Networks
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.
Preserving Fine-Grain Feature Information in Classification via Entropic Regularization
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.
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
Convolutional neural networks on irregular domains based on approximate vertex-domain translations
We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure.
Generalizing the Convolution Operator to extend CNNs to Irregular Domains
Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks.
Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation
Transfer learning using deep neural networks as feature extractors has become increasingly popular over the past few years.
Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs
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.
Robust Associative Memories Naturally Occuring From Recurrent Hebbian Networks Under Noise
In this paper, we are interested in demonstrating that those factors can actually lead to the appearance of robust associative memories.
Evaluating Graph Signal Processing for Neuroimaging Through Classification and Dimensionality Reduction
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.
Associative Memories to Accelerate Approximate Nearest Neighbor Search
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.
Memory vectors for similarity search in high-dimensional spaces
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.
Compression of Deep Neural Networks on the Fly
In this paper we introduce a novel compression method for deep neural networks that is performed during the learning phase.
Combating Corrupt Messages in Sparse Clustered Associative Memories
In this paper we analyze and extend the neural network based associative memory proposed by Gripon and Berrou.
Storing sequences in binary tournament-based neural networks
An extension to a recently introduced architecture of clique-based neural networks is presented.
Improving Sparse Associative Memories by Escaping from Bogus Fixed Points
The latter outperforms the former in terms of retrieval rate by a huge margin.
A study of retrieval algorithms of sparse messages in networks of neural cliques
We introduce several families of algorithms to enhance the retrieval process performance in recently proposed sparse associative memories based on binary neural networks.
Storing non-uniformly distributed messages in networks of neural cliques
Associative memories are data structures that allow retrieval of stored messages from part of their content.
A Massively Parallel Associative Memory Based on Sparse Neural Networks
In this paper we implement a variation of the Gripon-Berrou associative memory on a general purpose graphical processing unit (GPU).
Transfer Incremental Learning using Data Augmentation
Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power.
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Networks Robustness
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection.
Transfer Learning with Sparse Associative Memories
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.
Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectures to perform classification.
A Unified Deep Learning Formalism For Processing Graph Signals
Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images).
Comparing linear structure-based and data-driven latent spatial representations for sequence prediction
Predicting the future of Graph-supported Time Series (GTS) is a key challenge in many domains, such as climate monitoring, finance or neuroimaging.
Structural Robustness for Deep Learning Architectures
Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.
Improved Visual Localization via Graph Smoothing
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.
Efficient Hardware Implementation of Incremental Learning and Inference on Chip
In this paper, we tackle the problem of incrementally learning a classifier, one example at a time, directly on chip.
Training Modern Deep Neural Networks for Memory-Fault Robustness
Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging.
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
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.
Towards an Intrinsic Definition of Robustness for a Classifier
The robustness of classifiers has become a question of paramount importance in the past few years.
ThriftyNets : Convolutional Neural Networks with Tiny Parameter Budget
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.
Some Remarks on Replicated Simulated Annealing
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.
Representing Deep Neural Networks Latent Space Geometries with Graphs
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.
Gradients of Connectivity as Graph Fourier Bases of Brain Activity
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.
DecisiveNets: Training Deep Associative Memories to Solve Complex Machine Learning Problems
Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years.
Improving Classification Accuracy with Graph Filtering
In machine learning, classifiers are typically susceptible to noise in the training data.
Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks
The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs.
Quantization and Deployment of Deep Neural Networks on Microcontrollers
The quantization methods, relevant in the context of an embedded execution onto a microcontroller, are first outlined.
Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification
It is very common to face classification problems where the number of available labeled samples is small compared to their dimension.
Graphs as Tools to Improve Deep Learning Methods
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.
Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding
In this work, we are interested in better understanding what are the graph frequencies that are the most useful to decode fMRI signals.
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
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.
Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings
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.
Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities
BCI Motor Imagery datasets usually are small and have different electrodes setups.
Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach
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.
ThinResNet: A New Baseline for Structured Convolutional Networks Pruning
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.
Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples.
On Transfer in Classification: How Well do Subsets of Classes Generalize?
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.
Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding
In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches offline performance level while being usable online without requiring supervision.
LLM meets Vision-Language Models for Zero-Shot One-Class Classification
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.
