Vincent Gripon
YOU?
Author Swipe
View article: Object-Centric Cropping for Visual Few-Shot Classification
Object-Centric Cropping for Visual Few-Shot Classification Open
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 backgrounds can significantly deteriorate performance. Our resea…
View article: Anomalous Samples for Few-Shot Anomaly Detection
Anomalous Samples for Few-Shot Anomaly Detection Open
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 acquire. This hypothesis becomes questionable in Few-Shot set…
View article: Input Resolution Downsizing as a Compression Technique for Vision Deep Learning Systems
Input Resolution Downsizing as a Compression Technique for Vision Deep Learning Systems Open
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 methods for model compression have been proposed, most focu…
View article: Bit-Width-Aware Design Environment for Few-Shot Learning on Edge AI Hardware
Bit-Width-Aware Design Environment for Few-Shot Learning on Edge AI Hardware Open
International audience
View article: ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models
ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models Open
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 and versatility, efficient few-shot adaptation techniques hav…
View article: Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning
Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning Open
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 in multiple tasks. This makes the CI misleading in that it…
View article: LLM meets Vision-Language Models for Zero-Shot One-Class Classification
LLM meets Vision-Language Models for Zero-Shot One-Class Classification Open
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 available. This method aims to discriminate between positive and …
View article: Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding
Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding Open
In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches offline performance level while being usable online without requiring supervision. Interestingly, our method does not require retraining the model, as …
View article: Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes Open
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 ``target'' dataset or by directly adopting its representation as f…
View article: A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models
A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models Open
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 to simple transfer learning baselines. With the emergence of…
View article: Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning Open
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 works add text as an extra modality to enhance the performance …
View article: ThinResNet: A New Baseline for Structured Convolutional Networks Pruning
ThinResNet: A New Baseline for Structured Convolutional Networks Pruning Open
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. Of partic…
View article: A Strong and Simple Deep Learning Baseline for BCI MI Decoding
A Strong and Simple Deep Learning Baseline for BCI MI Decoding Open
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 to compare to, using only very standard ingredients from the…
View article: Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities
Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities Open
International audience
View article: Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach
Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach Open
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 training samples are available. The main solution consists in …
View article: A Statistical Model for Predicting Generalization in Few-Shot Classification
A Statistical Model for Predicting Generalization in Few-Shot Classification Open
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 shortcoming in the field. In these scenarios, it is common to r…
View article: Leveraging Structured Pruning of Convolutional Neural Networks
Leveraging Structured Pruning of Convolutional Neural Networks Open
Structured pruning is a popular method to reduce the cost of convolutional\nneural networks, that are the state of the art in many computer vision tasks.\nHowever, depending on the architecture, pruning introduces dimensional\ndiscrepancie…
View article: Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities
Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities Open
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 the amount of data available and hence obtain good general…
View article: Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings
Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings Open
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. This problem can be seen as a rival p…
View article: Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification Open
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. Especially in Few-Shot Classificati…
View article: Pruning Graph Convolutional Networks to Select Meaningful Graph Frequencies for FMRI Decoding
Pruning Graph Convolutional Networks to Select Meaningful Graph Frequencies for FMRI Decoding Open
International audience
View article: A Local Mixup to Prevent Manifold Intrusion
A Local Mixup to Prevent Manifold Intrusion Open
International audience
View article: Investigating the Not-So-Obvious Effects of Structured Pruning
Investigating the Not-So-Obvious Effects of Structured Pruning Open
International audience
View article: Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components
Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components Open
Few-shot classification aims at leveraging knowledge learned in a deep learning model, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a f…
View article: Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning Open
In many real-life problems, it is difficult to acquire or label large amounts of data, resulting in so-called few-shot learning problems. However, few-shot classification is a challenging problem due to the uncertainty caused by using few …
View article: Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding
Pruning Graph Convolutional Networks to select meaningful graph frequencies for fMRI decoding Open
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 brain. In this work, we are interested in better understandi…