Search Results for author: Stéphane Pateux

Found 13 papers, 5 papers with code

Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification

no code implementations18 Sep 2022 Yuqing Hu, Stéphane Pateux, Vincent Gripon

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.

Bayesian Inference Clustering +4

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

2 code implementations24 Jan 2022 Yassir Bendou, Yuqing Hu, Raphael Lafargue, Giulia Lioi, Bastien Pasdeloup, Stéphane Pateux, Vincent Gripon

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.

Few-Shot Image Classification Few-Shot Learning

Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning

no code implementations8 Nov 2019 Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux, Frédéric Jurie

This model outperforms its teacher on novel tasks, achieving results on par with state-of-the-art methods on 15 facial analysis tasks (and domains), at an affordable training cost.

Transfer Learning

Multi-Level Sensor Fusion with Deep Learning

no code implementations5 Nov 2018 Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux, Frédéric Jurie

In the context of deep learning, this article presents an original deep network, namely CentralNet, for the fusion of information coming from different sensors.

Sensor Fusion

CentralNet: a Multilayer Approach for Multimodal Fusion

2 code implementations22 Aug 2018 Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux, Frédéric Jurie

This paper proposes a novel multimodal fusion approach, aiming to produce best possible decisions by integrating information coming from multiple media.

Multi-Task Learning

CAKE: Compact and Accurate K-dimensional representation of Emotion

no code implementations30 Jul 2018 Corentin Kervadec, Valentin Vielzeuf, Stéphane Pateux, Alexis Lechervy, Frédéric Jurie

Alongside, Deep Neural Networks (DNN) are reaching excellent performances and are becoming interesting features extraction tools in many computer vision tasks. Inspired by works from the psychology community, we first study the link between the compact two-dimensional representation of the emotion known as arousal-valence, and discrete emotion classes (e. g. anger, happiness, sadness, etc.)

Emotion Recognition Facial Expression Recognition (FER)

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