Search Results for author: Céline Hudelot

Found 25 papers, 8 papers with code

StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data

no code implementations15 Oct 2021 Victor Pellegrain, Myriam Tami, Michel Batteux, Céline Hudelot

This paper tackles the problem of processing and combining efficiently arbitrary long data streams, coming from different modalities with different acquisition frequencies.

Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions

no code implementations21 Jun 2021 Martin Charachon, Paul-Henry Cournède, Céline Hudelot, Roberto Ardon

We show that visual explanation can be produced as the difference between two generated images obtained via two specific conditional generative models.

Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift

1 code implementation25 May 2021 Etienne Bennequin, Victor Bouvier, Myriam Tami, Antoine Toubhans, Céline Hudelot

To classify query instances from novel classes encountered at test-time, they only require a support set composed of a few labelled samples.

Few-Shot Learning Unsupervised Domain Adaptation

Spatial Contrastive Learning for Few-Shot Classification

1 code implementation26 Dec 2020 Yassine Ouali, Céline Hudelot, Myriam Tami

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.

Classification Contrastive Learning +2

AVAE: Adversarial Variational Auto Encoder

no code implementations21 Dec 2020 Antoine Plumerault, Hervé Le Borgne, Céline Hudelot

Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN).

Stochastic Adversarial Gradient Embedding for Active Domain Adaptation

no code implementations3 Dec 2020 Victor Bouvier, Philippe Very, Clément Chastagnol, Myriam Tami, Céline Hudelot

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.

Active Learning Unsupervised Domain Adaptation

Autoregressive Unsupervised Image Segmentation

1 code implementation ECCV 2020 Yassine Ouali, Céline Hudelot, Myriam Tami

In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs.

Representation Learning Unsupervised Image Segmentation +1

Target Consistency for Domain Adaptation: when Robustness meets Transferability

no code implementations25 Jun 2020 Yassine Ouali, Victor Bouvier, Myriam Tami, Céline Hudelot

Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation.

Image Classification Unsupervised Domain Adaptation

Robust Domain Adaptation: Representations, Weights and Inductive Bias

no code implementations24 Jun 2020 Victor Bouvier, Philippe Very, Clément Chastagnol, Myriam Tami, Céline Hudelot

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.

Unsupervised Domain Adaptation

An Overview of Deep Semi-Supervised Learning

1 code implementation9 Jun 2020 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 extensive collections of labeled data (e. g., ImageNet).

Image Classification

Semi-Supervised Semantic Segmentation with Cross-Consistency Training

5 code implementations CVPR 2020 Yassine Ouali, Céline Hudelot, Myriam Tami

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.

Semi-Supervised Semantic Segmentation

Controlling generative models with continuous factors of variations

1 code implementation ICLR 2020 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 natural language processing.


A New Approach for Explainable Multiple Organ Annotation with Few Data

no code implementations30 Dec 2019 Régis Pierrard, Jean-Philippe Poli, Céline Hudelot

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.

Domain-Invariant Representations: A Look on Compression and Weights

no code implementations25 Sep 2019 Victor Bouvier, Céline Hudelot, Clément Chastagnol, Philippe Very, Myriam Tami

Second, we show that learning weighted representations plays a key role in relaxing the constraint of invariance and then preserving the risk of compression.

Domain Adaptation

Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation

no code implementations29 Jul 2019 Victor Bouvier, Philippe Very, Céline Hudelot, Clément Chastagnol

Such approach consists in learning a representation of the data such that the label distribution conditioned on this representation is domain invariant.

Unsupervised Domain Adaptation

Learning Invariant Representations for Sentiment Analysis: The Missing Material is Datasets

no code implementations29 Jul 2019 Victor Bouvier, Philippe Very, Céline Hudelot, Clément Chastagnol

Learning representations which remain invariant to a nuisance factor has a great interest in Domain Adaptation, Transfer Learning, and Fair Machine Learning.

Domain Adaptation Sentiment Analysis +2

Learning Finer-class Networks for Universal Representations

no code implementations4 Oct 2018 Julien Girard, Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot

This raises the question of how well the original representation is "universal", that is to say directly adapted to many different target-tasks.

Relaxation-based revision operators in description logics

no code implementations26 Feb 2015 Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot

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.

Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics

no code implementations8 Feb 2015 Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.