Search Results for author: Frédéric Jurie

Found 25 papers, 6 papers with code

Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach

1 code implementation14 Sep 2023 Guillaume Jeanneret, Loïc Simon, Frédéric Jurie

This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classifier's prediction for a given image.

counterfactual Counterfactual Explanation

Adversarial Counterfactual Visual Explanations

1 code implementation CVPR 2023 Guillaume Jeanneret, Loïc Simon, Frédéric Jurie

Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.

counterfactual Counterfactual Explanation +1

Diffusion Models for Counterfactual Explanations

1 code implementation29 Mar 2022 Guillaume Jeanneret, Loïc Simon, Frédéric Jurie

Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable.

counterfactual

On the inductive biases of deep domain adaptation

no code implementations16 Sep 2021 Rodrigue Siry, Louis Hémadou, Loïc Simon, Frédéric Jurie

Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain.

Unsupervised Domain Adaptation

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

n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error

no code implementations20 Aug 2019 Michel Moukari, Loïc Simon, Sylvaine Picard, Frédéric Jurie

As deep learning applications are becoming more and more pervasive in robotics, the question of evaluating the reliability of inferences becomes a central question in the robotics community.

Monocular Depth Estimation

Semantic bottleneck for computer vision tasks

no code implementations6 Nov 2018 Maxime Bucher, Stéphane Herbin, Frédéric Jurie

This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks.

Content-Based Image Retrieval General Classification +2

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.

Deep Learning Sensor Fusion

MERCI: A NEW METRIC TO EVALUATE THE CORRELATION BETWEEN PREDICTIVE UNCERTAINTY AND TRUE ERROR

no code implementations27 Sep 2018 Michel Moukari, Loïc Simon, Sylvaine Picard, Frédéric Jurie

One contribution of this article is to draw attention on existing metrics developed in the forecast community, designed to evaluate both the sharpness and the calibration of predictive uncertainty.

Deep Learning Monocular Depth Estimation +1

RPNet: an End-to-End Network for Relative Camera Pose Estimation

1 code implementation22 Sep 2018 Sovann En, Alexis Lechervy, Frédéric Jurie

While state-of-the-art systems based on SIFT + RANSAC, are able to recover the translation vector only up to scale, RPNet is trained to produce the full translation vector, in an end-to-end way.

Camera Pose Estimation Pose Estimation +1

Faster RER-CNN: application to the detection of vehicles in aerial images

no code implementations20 Sep 2018 Jean Ogier du Terrail, Frédéric Jurie

Detecting small vehicles in aerial images is a difficult job that can be challenging even for humans.

Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks

no code implementations10 Sep 2018 Shivang Agarwal, Jean Ogier du Terrail, Frédéric Jurie

Object detection-the computer vision task dealing with detecting instances of objects of a certain class (e. g., 'car', 'plane', etc.)

Object object-detection +2

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.)

Ranked #28 on Facial Expression Recognition (FER) on AffectNet (Accuracy (7 emotion) metric)

Emotion Recognition Facial Expression Recognition (FER)

Deep multi-scale architectures for monocular depth estimation

no code implementations8 Jun 2018 Michel Moukari, Sylvaine Picard, Loic Simon, Frédéric Jurie

This paper aims at understanding the role of multi-scale information in the estimation of depth from monocular images.

Monocular Depth Estimation

TS-Net: Combining modality specific and common features for multimodal patch matching

1 code implementation5 Jun 2018 Sovann En, Alexis Lechervy, Frédéric Jurie

Multimodal patch matching addresses the problem of finding the correspondences between image patches from two different modalities, e. g. RGB vs sketch or RGB vs near-infrared.

Multimodal Patch Matching

Generating Visual Representations for Zero-Shot Classification

no code implementations23 Aug 2017 Maxime Bucher, Stéphane Herbin, Frédéric Jurie

This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e. g. visual attributes) while the others are defined by exemplar images as well.

Classification General Classification +1

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