Nicolas Gonthier

Nicolas Gonthier
Institut national de l’information géographique et forestière | IGN

Doctor of Philosophy

About

20
Publications
2,100
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
246
Citations
Introduction
Additional affiliations
April 2017 - September 2017
Institut Mines-Télécom
Position
  • Intern
February 2016 - July 2016
National Institute of Information and Communications Technology
Position
  • Intern
July 2015 - December 2015
Cea Leti
Position
  • Intern

Publications

Publications (20)
Preprint
Full-text available
Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose AnySat, a multimodal model based on joint embedding predictive architecture (JEPA) and resolution-adaptive spa...
Preprint
Full-text available
Object detection in art is a valuable tool for the digital humanities, as it allows for faster identification of objects in artistic and historical images compared to humans. However, annotating such images poses significant challenges due to the need for specialized domain expertise. We present NADA (no annotations for detection in art), a pipelin...
Conference Paper
Full-text available
We introduce the French Land cover from Aerospace ImageRy (FLAIR), an extensive dataset from the French National Institute of Geographical and Forest Information (IGN) that provides a unique and rich resource for large-scale geospatial analysis. FLAIR contains high-resolution aerial imagery with a ground sample distance of 20 cm and over 20 billion...
Preprint
Full-text available
Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, annotating large datasets to develop supervised systems for remote sensing (RS) semantic segmentation is costly and time-consuming. Unsupervised Domain Adaption (UDA) could tackle these issues by adapting a model trained on a source domain, where...
Preprint
Full-text available
We present a generative document-specific approach to character analysis and recognition in text lines. Our main idea is to build on unsupervised multi-object segmentation methods and in particular those that reconstruct images based on a limited amount of visual elements, called sprites. Our approach can learn a large number of different character...
Article
Full-text available
The field of texture synthesis has witnessed important progresses over the last years, most notably through the use of convolutional neural networks. However, neural synthesis methods still struggle to reproduce large-scale structures, especially with high-resolution textures. To address this issue, we first introduce a simple multi-resolution fram...
Article
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performance...
Thesis
In this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural images to related tasks. We follow two axes: texture synthesis and visual recognition in artworks. The first one consists in synthesizing a new image given a reference sample. Most methods are based on enforcing the Gram matrices of ImageNet-trained CNN...
Chapter
Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer learning are still poorly understood. In this paper, we first use techniques for visualizing the network inter...
Preprint
Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer learning are still poorly understood. In this paper, we first use techniques for visualizing the network inter...
Preprint
Full-text available
The field of texture synthesis has witnessed important progresses over the last years, most notably through the use of Convolutional Neural Networks. However, neural synthesis methods still struggle to reproduce large scale structures, especially with high resolution textures. To address this issue, we first introduce a simple multi-resolution fram...
Preprint
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performance...
Preprint
Full-text available
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects....
Chapter
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects....
Article
Full-text available
Individuals often have reduced ability to hear alarms in real world situations (e.g., anesthesia monitoring, flying airplanes) when attention is focused on another task, sometimes with devastating consequences. This phenomenon is called inattentional deafness and usually occurs under critical high workload conditions. It is difficult to simulate th...
Article
Full-text available
Inattentional deafness is the failure to hear otherwise audible sounds (usually alarms) that may occur under high workload conditions. One potential cause for its occurrence could be an attentional bottleneck that occurs when task demands are high, resulting in lack of resources for processing of additional tasks. In this fMRI experiment, we explor...

Network

Cited By