709 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Toulouse III - Paul SabatierFR432 papers
- Université Toulouse - Jean JaurèsFR332 papers
- Université Toulouse-I-CapitoleFR331 papers
- Institut Polytechnique de BordeauxFR326 papers
- Centre National de la Recherche ScientifiqueFR253 papers
- Université de ToulouseFR159 papers
- Institut National Polytechnique de ToulouseFR101 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR92 papers
- École Nationale Supérieure d'Électrotechnique, d'Électronique, d'Informatique, d'Hydraulique et des TélécommunicationsFR52 papers
- Institut national de recherche en sciences et technologies du numériqueFR26 papers
- Institut Universitaire de FranceFR19 papers
- Sorbonne UniversitéFR19 papers
51 papers · 1 filter
LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Vincent Lébé, Yannick Prudent, Corentin Friedrich +3
Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their a…
MoonAnything: A Vision Benchmark with Large-Scale Lunar Supervised Data
Clémentine Grethen, Yuang Shi, Simone Gasparini +1
Accurate perception of lunar surfaces is critical for modern lunar exploration missions. However, developing robust learning-based perception systems is hindered by the lack of dat…
Fast and Flexible Robustness Certificates for Semantic Segmentation
Thomas Massena, Corentin Friedrich, Franck Mamalet +1
Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust De…
Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset
Clementine Grethen, Simone Gasparini, Geraldine Morin +3
Accurate 3D reconstruction of lunar surfaces is essential for space exploration. However, existing stereo vision reconstruction methods struggle in this context due to the Moon's l…
Annotating Satellite Images of Forests with Keywords from a Specialized Corpus in the Context of Change Detection
Nathalie Neptune, Josiane Mothe
The Amazon rain forest is a vital ecosystem that plays a crucial role in regulating the Earth's climate and providing habitat for countless species. Deforestation in the Amazon is…
Sketchpose: Learning to Segment Cells with Partial Annotations
Clément Cazorla, Nathanaël Munier, Renaud Morin +1
The most popular networks used for cell segmentation (e.g. Cellpose, Stardist, HoverNet,...) rely on a prediction of a distance map. It yields unprecedented accuracy but hinges on…
Light and 3D: a methodological exploration of digitisation techniques adapted to a selection of objects from the Mus{é}e d'Arch{é}ologie Nationale
Antoine Laurent, Jean Mélou, Catherine Schwab +5
The need to digitize heritage objects is now widely accepted. This article presents the very fashionable context of the creation of ''digital twins''. It illustrates the diversity…
AgriPotential: A Novel Multi-Spectral and Multi-Temporal Remote Sensing Dataset for Agricultural Potentials
Mohammad El Sakka, Caroline De Pourtales, Lotfi Chaari +1
Remote sensing has emerged as a critical tool for large-scale Earth monitoring and land management. In this paper, we introduce AgriPotential, a novel benchmark dataset composed of…
Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes
Yuang Shi, Simone Gasparini, Géraldine Morin +2
3D Gaussian Splatting (3DGS) has emerged as a promising representation for photorealistic rendering of 3D scenes. However, its high storage requirements pose significant challenges…
Deep priors for satellite image restoration with accurate uncertainties
Biquard Maud, Marie Chabert, Florence Genin +2
Satellite optical images, upon their on-ground receipt, offer a distorted view of the observed scene. Their restoration, including denoising, deblurring, and sometimes super-resolu…
A Note on Geometric Calibration of Multiple Cameras and Projectors
Tomislav Petkovic, Simone Gasparini, Tomislav Pribanic
Geometric calibration of cameras and projectors is an essential step that must be performed before any imaging system can be used. There are many well-known geometric calibration m…
LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming
Yuang Shi, Géraldine Morin, Simone Gasparini +1
The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. This pa…
Understanding Visual Feature Reliance through the Lens of Complexity
Thomas Fel, Louis Bethune, Andrew Kyle Lampinen +2
Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus…
Robust Confidence Intervals in Stereo Matching using Possibility Theory
Roman Malinowski, Emmanuelle Sarrazin, Loïc Dumas +2
We propose a method for estimating disparity confidence intervals in stereo matching problems. Confidence intervals provide complementary information to usual confidence measures.…
RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction
Baptiste Brument, Robin Bruneau, Yvain Quéau +5
This paper introduces a versatile paradigm for integrating multi-view reflectance (optional) and normal maps acquired through photometric stereo. Our approach employs a pixel-wise…
Variational Bayes image restoration with compressive autoencoders
Maud Biquard, Marie Chabert, Florence Genin +2
Regularization of inverse problems is of paramount importance in computational imaging. The ability of neural networks to learn efficient image representations has been recently ex…
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or…
Kartezio: Evolutionary Design of Explainable Pipelines for Biomedical Image Analysis
Kévin Cortacero, Brienne McKenzie, Sabina Müller +14
An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in…
Video-based Human Action Recognition using Deep Learning: A Review
Hieu H. Pham, Louahdi Khoudour, Alain Crouzil +2
Human action recognition is an important application domain in computer vision. Its primary aim is to accurately describe human actions and their interactions from a previously uns…
Dilated convolution with learnable spacings
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
Recent works indicate that convolutional neural networks (CNN) need large receptive fields (RF) to compete with visual transformers and their attention mechanism. In CNNs, RFs can…
Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
Bhavin Choksi, Milad Mozafari, Callum Biggs O'May +3
Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shor…
Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection
Ismat Ara Reshma, Sylvain Cussat-Blanc, Radu Tudor Ionescu +2
The class distribution of data is one of the factors that regulates the performance of machine learning models. However, investigations on the impact of different distributions ava…
Dynamic Multi-Task Learning for Face Recognition with Facial Expression
Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman +2
Benefiting from the joint learning of the multiple tasks in the deep multi-task networks, many applications have shown the promising performance comparing to single-task learning.…
Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension
Geoffrey Roman-Jimenez, Patrice Guyot, Thierry Malon +7
This paper addresses the problem of vehicle re-identification using distance comparison of images in CNN latent spaces. Firstly, we study the impact of the distance metrics, compar…