244 citations · 366 across the 25 of their papers we have counts for
17 papers · 1 filter
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Grégoire Petit, Michael Soumm, Eva Feillet +4
Class-Incremental Learning (CIL) aims to build classification models from data streams. At each step of the CIL process, new classes must be integrated into the model. Due to catas…
Test-Time Adaptation with Principal Component Analysis
Thomas Cordier, Victor Bouvier, Gilles Hénaff +1
Machine Learning models are prone to fail when test data are different from training data, a situation often encountered in real applications known as distribution shift. While sti…
Model-Agnostic Few-Shot Open-Set Recognition
Malik Boudiaf, Etienne Bennequin, Myriam Tami +4
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have few labeled samples, while simultaneously dete…
Towards Job-Transition-Tag Graph for a Better Job Title Representation Learning
Jun Zhu, Céline Hudelot
Works on learning job title representation are mainly based on \textit{Job-Transition Graph}, built from the working history of talents. However, since these records are usually me…
Minority Class Oriented Active Learning for Imbalanced Datasets
Umang Aggarwal, Adrian Popescu, Céline Hudelot
Active learning aims to optimize the dataset annotation process when resources are constrained. Most existing methods are designed for balanced datasets. Their practical applicabil…
A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning
Umang Aggarwal, Adrian Popescu, Eden Belouadah +1
Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the cap…
StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data
Victor Pellegrain, Myriam Tami, Michel Batteux +1
The increasing complexity of Industry 4.0 systems brings new challenges regarding predictive maintenance tasks such as fault detection and diagnosis. A corresponding and realistic…
Demystifying Drug Repurposing Domain Comprehension with Knowledge Graph Embedding
Edoardo Ramalli, Alberto Parravicini, Guido Walter Di Donato +3
Drug repurposing is more relevant than ever due to drug development's rising costs and the need to respond to emerging diseases quickly. Knowledge graph embedding enables drug repu…
Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions
Martin Charachon, Paul-Henry Cournède, Céline Hudelot +1
Providing a human-understandable explanation of classifiers' decisions has become imperative to generate trust in their use for day-to-day tasks. Although many works have addressed…
Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift
Etienne Bennequin, Victor Bouvier, Myriam Tami +2
Few-Shot Learning (FSL) algorithms have made substantial progress in learning novel concepts with just a handful of labelled data. To classify query instances from novel classes en…
Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
Victor Bouvier, Philippe Very, Clément Chastagnol +2
Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. I…
An Overview of Deep Semi-Supervised Learning
Yassine Ouali, Céline Hudelot, Myriam Tami
Deep neural networks demonstrated their ability to provide remarkable performances on a wide range of supervised learning tasks (e.g., image classification) when trained on extensi…
Target Consistency for Domain Adaptation: when Robustness meets Transferability
Yassine Ouali, Victor Bouvier, Myriam Tami +1
Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation. By investigating the robustness of…
Robust Domain Adaptation: Representations, Weights and Inductive Bias
Victor Bouvier, Philippe Very, Clément Chastagnol +2
Unsupervised Domain Adaptation (UDA) has attracted a lot of attention in the last ten years. The emergence of Domain Invariant Representations (IR) has improved drastically the tra…
Controlling generative models with continuous factors of variations
Antoine Plumerault, Hervé Le Borgne, Céline Hudelot
Recent deep generative models are able to provide photo-realistic images as well as visual or textual content embeddings useful to address various tasks of computer vision and natu…
Learning Invariant Representations for Sentiment Analysis: The Missing Material is Datasets
Victor Bouvier, Philippe Very, Céline Hudelot +1
Learning representations which remain invariant to a nuisance factor has a great interest in Domain Adaptation, Transfer Learning, and Fair Machine Learning. Finding such represent…
Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
Victor Bouvier, Philippe Very, Céline Hudelot +1
Unsupervised Domain Adaptation aims to learn a model on a source domain with labeled data in order to perform well on unlabeled data of a target domain. Current approaches focus on…