Search Results for author:
Found 39 papers, 14 papers with code
An Overview of Deep Semi-Supervised Learning
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 extensive collections of labeled data (e. g., ImageNet).
Semi-Supervised Semantic Segmentation with Cross-Consistency Training
To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations.
Spatial Contrastive Learning for Few-Shot Classification
In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features.
Open-Set Likelihood Maximization for Few-Shot Learning
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i. e. classifying instances among a set of classes for which we only have a few labeled samples, while simultaneously detecting instances that do not belong to any known class.
Représentations lexicales pour la détection non supervisée d'événements dans un flux de tweets : étude sur des corpus français et anglais
In this work, we evaluate the performance of recent text embeddings for the automatic detection of events in a stream of tweets.
Autoregressive Unsupervised Image Segmentation
In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs.
Ranked #5 on
Unsupervised Semantic Segmentation
on COCO-Stuff-3
Controlling generative models with continuous factors of variations
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 natural language processing.
Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift
To classify query instances from novel classes encountered at test-time, they only require a support set composed of a few labelled samples.
Towards Job-Transition-Tag Graph for a Better Job Title Representation Learning
Works on learning job title representation are mainly based on \textit{Job-Transition Graph}, built from the working history of talents.
Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
Instruction Fine-Tuning (IFT) is a powerful paradigm that strengthens the zero-shot capabilities of Large Language Models (LLMs), but in doing so induces new evaluation metric requirements.
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Deploying large language models (LLMs) of several billion parameters can be impractical in most industrial use cases due to constraints such as cost, latency limitations, and hardware accessibility.
Learning More Universal Representations for Transfer-Learning
We also propose a unified framework of the methods based on the diversifying of the training problem.
CroissantLLM: A Truly Bilingual French-English Language Model
We introduce CroissantLLM, a 1. 3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware.
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
Neural Information Retrieval (NIR) has significantly improved upon heuristic-based IR systems.
Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics
Belief revision of knowledge bases represented by a set of sentences in a given logic has been extensively studied but for specific logics, mainly propositional, and also recently Horn and description logics.
Relaxation-based revision operators in description logics
In this paper we address both the generalization of the well-known AGM postulates, and the definition of concrete and well-founded revision operators in different DL families.
Combinaison d'information visuelle, conceptuelle, et contextuelle pour la construction automatique de hierarchies semantiques adaptees a l'annotation d'images
Therefore, the built hierarchy is used in a semantic hierarchical classification framework for image annotation.
Learning Finer-class Networks for Universal Representations
This raises the question of how well the original representation is "universal", that is to say directly adapted to many different target-tasks.
Learning Invariant Representations for Sentiment Analysis: The Missing Material is Datasets
Learning representations which remain invariant to a nuisance factor has a great interest in Domain Adaptation, Transfer Learning, and Fair Machine Learning.
Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
Such approach consists in learning a representation of the data such that the label distribution conditioned on this representation is domain invariant.
A New Approach for Explainable Multiple Organ Annotation with Few Data
In this paper, we focus on organ annotation in medical images and we introduce a reasoning framework that is based on learning fuzzy relations on a small dataset for generating explanations.
Robust Domain Adaptation: Representations, Weights and Inductive Bias
The emergence of Domain Invariant Representations (IR) has improved drastically the transferability of representations from a labelled source domain to a new and unlabelled target domain.
Target Consistency for Domain Adaptation: when Robustness meets Transferability
Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation.
Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
First, we select for annotation target samples that are likely to improve the representations' transferability by measuring the variation, before and after annotation, of the transferability loss gradient.
Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification
From a given classifier, we train two generators to produce from an input image the so called similar and adversarial images.
AVAE: Adversarial Variational Auto Encoder
Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN).
Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions
We show that visual explanation can be produced as the difference between two generated images obtained via two specific conditional generative models.
Demystifying Drug Repurposing Domain Comprehension with Knowledge Graph Embedding
Drug repurposing is more relevant than ever due to drug development's rising costs and the need to respond to emerging diseases quickly.
StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data
The increasing complexity of Industry 4. 0 systems brings new challenges regarding predictive maintenance tasks such as fault detection and diagnosis.
Improving Next-Application Prediction with Deep Personalized-Attention Neural Network
The second module learns job seeker representations.
Domain-Invariant Representations: A Look on Compression and Weights
Second, we show that learning weighted representations plays a key role in relaxing the constraint of invariance and then preserving the risk of compression.
Optimizing Active Learning for Low Annotation Budgets
It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in order to improve the previous model and gain in generalization.
Minority Class Oriented Active Learning for Imbalanced Datasets
Here, we introduce a new active learning method which is designed for imbalanced datasets.
A Comparative Study of Calibration Methods for Imbalanced Class Incremental Learning
Since memory is bounded, old classes are learned with fewer images than new classes and an imbalance due to incremental learning is added to the initial dataset imbalance.
Test-Time Adaptation with Principal Component Analysis
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.
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.
Improving Neural-based Classification with Logical Background Knowledge
We develop a new multi-scale methodology to evaluate how the benefits of a neurosymbolic technique evolve with the scale of the network.
Recommendation of data-free class-incremental learning algorithms by simulating future data
Our method outperforms competitive baselines, and performance is close to that of an oracle choosing the best algorithm in each setting.
Complexity of Probabilistic Reasoning for Neurosymbolic Classification Techniques
Informed multi-label classification is a sub-field of neurosymbolic AI which studies how to leverage prior knowledge to improve neural classification systems.
