Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
publications
Trading sharpness with energy consumption in a lens autofocus application
Molnos, A. (2016). "Trading sharpness with energy consumption in a lens autofocus application" Workshop on Approximate Computing, Embedded Systems Week.
This paper is about approximate computing on embedded system.
Neural signature of inattentional deafness
Durantin, G. (2017). "Neural signature of inattentional deafness" Human Brain Mapping.
This paper is about inattentional deafness of pilot in stressful conditions.
Disruption in Neural Phase Synchrony is Related to Identification of Inattentional Deafness in Real-World Setting
Callan, D. (2018). "Disruption in Neural Phase Synchrony is Related to Identification of Inattentional Deafness in Real-World Setting" Human brain mapping.
This work is about inattentional deafness in real world flying conditions.
Weakly Supervised Object Detection in Artworks
Gonthier, N. (2018). "Weakly Supervised Object Detection in Artworks" Workshop on Computer Vision for Art Analysis ECCV.
This paper is about weakly supervised object in artworks thanks to pretrained features extraction and multiple instance learning.
Transfert d’apprentissage et visualisation de réseaux de neurones pour les images artistiques
Gonthier, N. (2020). "Transfert d'apprentissage et visualisation de réseaux de neurones pour les images artistiques" DHNord, The Measurement of Images. Computational Approaches in the History and Theory of the Arts..
Study of Transfer Learning from natural images to artistic ones, based on feature visualization of CNN.
An analysis of the transfer learning of convolutional neural networks for artistic images
Gonthier, N. (2020). "An analysis of the transfer learning of convolutional neural networks for artistic images" Workshop on Fine Art Pattern Extraction and Recognition ICPR.
This paper is about CNN analysis with feature visualisation and quantitative metrics. We study the transfer learning from natural images to artistic ones.
Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
Gonthier, N. (2022). "Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts" Computer Vision and Image Understanding.
This paper is about weakly supervised object in artworks (paintings, watercolor etc) based on multiple instance learning. We propose a simple multiple instance approach applied on pre-trained deep features to learn new classes on non-photographic datasets.
High resolution neural texture synthesis with long range constraints
Gonthier, N. (2022). "High resolution neural texture synthesis with long range constraints" Journal of Mathematical Imaging and Vision.
This paper is about texture synthesis with CNN, we proposed a Multiscale strategy. We show that additional statistical constraints further improve the reproduction of textures with strong regularity (spectrum or autocorrelation).
GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates
Marsocci V. (2023). "GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates" CVPR Workshops EarthVision.
This paper is about domain adaptation in remote sensing based on using geographical coordinates of the patches.
FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery
Garioud A. (2023). "FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery" NeurIPS Datasets and Benchmarks Track.
This paper is about land cover semantic segmentation and multi modalities fusion (very high resolution aerial image and satellite time series).
The Learnable Typewriter: A Generative Approach to Text Line Analysis
Siglidis, I. (2024). " The Learnable Typewriter: A Generative Approach to Text Line Analysis " ICDAR.
This paper is about unsupervised text recognition based on analysis-by-synthesis method.
StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
Wu S. (2024). "StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translationy" CVPR.
This paper is about leveaging steganography in GAN for non-bijective image translation, avoiding spurious synthesis and detecting mismatched features.
OmniSat: Self-Supervised Modality Fusion for Earth Observation
Astruc G. (2024). "OmniSat: Self-Supervised Modality Fusion for Earth Observation" ECCV.
This paper is about self-supervised multimodal learning modal for more efficient training scheme (with very high resolution aerial image and satellite time series).
No Annotations for Object Detection in Art through Stable Diffusion
Ramos P. (2025). "No Annotations for Object Detection in Art through Stable Diffusion" WACV.
This paper proposed a new method for weakly supervised and zero shot object detection in artworks. It leverages a large vision language model and we propose a class-conditioned detector based on Stable Diffusion for object localization.
Operational Change Detection for Geographical Information: Overview and Challenges
Gonthier N. (2025). "Operational Change Detection for Geographical Information: Overview and Challenges" preprint.
This paper is an overview about operational change detection.
The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation
Benidir Y. (2025). " The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation" CVPR.
This paper is about a new pipeline to create a hybrid semantic change detection dataset for pretraining models. We provide a comprehensive evaluation of transfer learning on 5 different datasets and 4 scenarios.
AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities
Astruc G. (2025). "AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities" CVPR.
This paper is about AnySat: a JEPA-based multimodal Earth Observation model that trains simultaneously on diverse datasets with different scales, resolutions (spatial, spectral, temporal), and modality combinations.
talks
Weakly Supervised Learning in Artworks
Talk during the Journée “Supervision faible ou apprentissage non supervisé pour l’analyse d’images et de vidéos” from GDR ISIS, May 2019.
PhD Defense
PhD Defense from Télécom Paris - Université Paris Saclay with the following commite :
- Agnès Desolneux, CNRS, ENS Paris-Saclay, France
- Mathieu Aubry , ENPC, France
- Javier Portilla, CSIC, Espagne
- Thomas Hurtut, Polytechnique Montréal, Canada
- Sabine Süsstrunk, EPFL, Suisse
- Yann Gousseau, Télécom Paris, France
- Saïd Ladjal, Télécom Paris, France
- Olivier Bonfait, Université de Bourgogne, France
Détection de changement dans les données géospatiales
Organisation de la journée GDR IASIS - GDR MADICS “Détection de changement dans les données géospatiales”, le vendredi 21 mars au CNAM Paris :
- Deux présentations invités
- 13 oraux par diverses équipes de recherche française
teaching
Signal and Image processing teaching assistant
Undergraduate course (L3), Télécom Paris, 2017
Signal and Image processing Practical sessions (TP) :
- 2017-2018 : 15h
- 2018-2019 : 15h
- 2019-2020 : 32h
Machine Learning for Image Analysis
(M1), Télécom Paris, 2018
Machine Learning for Image Analysis : Organization of a data challenge :
- 2018 : Melanome classification
- 2019 : Melanome classification
- 2020 : Paintings classification
Introduction to image processing and artificial intelligence
(M1), Université de Bourgogne, 2018
Introduction to image processing and artificial intelligence for master students in art history :
- 2018 : 5h
- 2019 : 5h
- 2021 : 3h
Student Project Supervision
(M1), Télécom Paris, 2018
Machine Learning and Image Processing, student project supervision :
- 2018 : Style Transfer with CNN
- 2019 : Style classification with CNN
- 2020 : Style classification with CNN
Deep Learning teaching assistant
Graduate course (M2), Télécom Paris, 2019
Student Projects Supervision in Computer Vision
(M1), École nationale des ponts et chaussées (ENPC), 2021
Student Projects Supervision (26h) :
- Image clustering in ancient manuscripts.
- Image Retrieval in Artworks database
Introduction à la vision par ordinateur
(M1), École Nationale Supérieure d'Architecture (ENSA) Paris-Malaquais, 2021
Introduction à la vision par ordinateur pour des étudiants en école d’architecture (3h).