Search Results for author: Nicolas Thome

Found 61 papers, 37 papers with code

Supra-Laplacian Encoding for Transformer on Dynamic Graphs

1 code implementation26 Sep 2024 Yannis Karmim, Marc Lafon, Raphael Fournier S'niehotta, Nicolas Thome

Fully connected Graph Transformers (GT) have rapidly become prominent in the static graph community as an alternative to Message-Passing models, which suffer from a lack of expressivity, oversquashing, and under-reaching.

Dynamic Link Prediction

Temporal receptive field in dynamic graph learning: A comprehensive analysis

1 code implementation17 Jul 2024 Yannis Karmim, Leshanshui Yang, Raphaël Fournier S'Niehotta, Clément Chatelain, Sébastien Adam, Nicolas Thome

Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges.

Benchmarking Dynamic Link Prediction +2

ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation

no code implementations3 Jul 2024 Yannis Karmim, Elias Ramzi, Raphaël Fournier-S'niehotta, Nicolas Thome

Moreover, we extend the evaluation of GNN models for top-k recommendation tasks with an inductive user-centric protocol, providing a more accurate reflection of real-world applications.

Collaborative Filtering

Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning

1 code implementation2 Jul 2024 Zakariae El Asri, Olivier Sigaud, Nicolas Thome

Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time.

Reinforcement Learning (RL)

GalLoP: Learning Global and Local Prompts for Vision-Language Models

1 code implementation1 Jul 2024 Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas Audebert, Nicolas Thome

Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e. g. in domain generalization or out-of-distribution (OOD) detection.

Diversity Domain Generalization +2

Energy Correction Model in the Feature Space for Out-of-Distribution Detection

no code implementations15 Mar 2024 Marc Lafon, Clément Rambour, Nicolas Thome

In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification

no code implementations15 Jan 2024 Nathan Painchaud, Jérémie Stym-Popper, Pierre-Yves Courand, Nicolas Thome, Pierre-Marc Jodoin, Nicolas Duchateau, Olivier Bernard

Deep learning enables automatic and robust extraction of cardiac function descriptors from echocardiographic sequences, such as ejection fraction or strain.

Ordinal Classification

TRUSTED: The Paired 3D Transabdominal Ultrasound and CT Human Data for Kidney Segmentation and Registration Research

no code implementations19 Oct 2023 William Ndzimbong, Cyril Fourniol, Loic Themyr, Nicolas Thome, Yvonne Keeza, Beniot Sauer, Pierre-Thierry Piechaud, Arnaud Mejean, Jacques Marescaux, Daniel George, Didier Mutter, Alexandre Hostettler, Toby Collins

To validate the dataset's utility, 5 competitive Deep Learning models for automatic kidney segmentation were benchmarked, yielding average DICE scores from 83. 2% to 89. 1% for CT, and 61. 9% to 79. 4% for US images.

Image Registration Image Segmentation +2

Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks

1 code implementation13 Jul 2023 Denis Coquenet, Clément Rambour, Emanuele Dalsasso, Nicolas Thome

Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs.

Attribute

VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing

no code implementations14 Jun 2023 Paul Couairon, Clément Rambour, Jean-Emmanuel Haugeard, Nicolas Thome

In this work, we introduce VidEdit, a novel method for zero-shot text-based video editing that guarantees robust temporal and spatial consistency.

Image Generation Video Editing

Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection

1 code implementation26 May 2023 Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas Thome

HEAT complements prior density estimators of the ID density, e. g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation.

Density Estimation Out-of-Distribution Detection +1

Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers

1 code implementation16 Feb 2023 Steeven Janny, Aurélien Béneteau, Madiha Nadri, Julie Digne, Nicolas Thome, Christian Wolf

To perform future forecasting of pressure and velocity on the challenging EAGLE dataset, we introduce a new mesh transformer.

Node Clustering

Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints

1 code implementation7 Feb 2023 Laura Calem, Hedi Ben-Younes, Patrick Pérez, Nicolas Thome

Predicting multiple trajectories for road users is important for automated driving systems: ego-vehicle motion planning indeed requires a clear view of the possible motions of the surrounding agents.

Diversity Motion Planning +2

Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation

no code implementations15 Dec 2022 Loic Themyr, Clement Rambour, Nicolas Thome, Toby Collins, Alexandre Hostettler

In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens.

Semantic Segmentation

Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval

1 code implementation8 Dec 2022 Mustafa Shukor, Nicolas Thome, Matthieu Cord

Finally, we validate the generalization of the approach to other tasks (i. e, Food Recognition) and domains with structured text such as the Medical domain on the ROCO dataset.

Cross-Modal Retrieval Food Recognition +1

Take One Gram of Neural Features, Get Enhanced Group Robustness

no code implementations26 Aug 2022 Simon Roburin, Charles Corbière, Gilles Puy, Nicolas Thome, Matthieu Aubry, Renaud Marlet, Patrick Pérez

Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts.

Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction

1 code implementation8 Jul 2022 Vincent Le Guen, Clément Rambour, Nicolas Thome

Since BC is an approximate physical model violated in several situations, we propose to train a physically-constrained network complemented with a data-driven network.

Optical Flow Estimation Uncertainty Quantification

Hierarchical Average Precision Training for Pertinent Image Retrieval

2 code implementations5 Jul 2022 Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot

Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity.

Image Retrieval Metric Learning

Towards efficient feature sharing in MIMO architectures

no code implementations20 May 2022 Rémy Sun, Alexandre Ramé, Clément Masson, Nicolas Thome, Matthieu Cord

To solve this issue, we propose a novel unmixing step in MIMO architectures that allows subnetworks to properly share features.

Swapping Semantic Contents for Mixing Images

no code implementations20 May 2022 Rémy Sun, Clément Masson, Gilles Hénaff, Nicolas Thome, Matthieu Cord

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data.

Data Augmentation

Effective Uncertainty Estimation with Evidential Models for Open-World Recognition

no code implementations29 Sep 2021 Charles Corbière, Marc Lafon, Nicolas Thome, Matthieu Cord, Patrick Perez

A crucial property of KLoS is to be a class-wise divergence measure built from in-distribution samples and to not require OOD training data, in contrast to current second-order uncertainty measures.

Deep Time Series Forecasting with Shape and Temporal Criteria

1 code implementation9 Apr 2021 Vincent Le Guen, Nicolas Thome

This paper addresses the problem of multi-step time series forecasting for non-stationary signals that can present sudden changes.

Change Detection Diversity +3

U-Net Transformer: Self and Cross Attention for Medical Image Segmentation

2 code implementations10 Mar 2021 Olivier Petit, Nicolas Thome, Clément Rambour, Luc Soler

Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures.

Decoder Image Segmentation +3

Confidence Estimation via Auxiliary Models

no code implementations11 Dec 2020 Charles Corbière, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP).

Domain Adaptation Image Classification +1

Probabilistic Time Series Forecasting with Shape and Temporal Diversity

1 code implementation NeurIPS 2020 Vincent Le Guen, Nicolas Thome

We introduce the STRIPE model for representing structured diversity based on shape and time features, ensuring both probable predictions while being sharp and accurate.

Diversity Point Processes +2

Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity

1 code implementation14 Oct 2020 Vincent Le Guen, Nicolas Thome

We introduce the STRIPE model for representing structured diversity based on shape and time features, ensuring both probable predictions while being sharp and accurate.

Diversity Point Processes +2

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

2 code implementations ICLR 2021 Yuan Yin, Vincent Le Guen, Jérémie Dona, Emmanuel de Bézenac, Ibrahim Ayed, Nicolas Thome, Patrick Gallinari

In this work, we introduce the APHYNITY framework, a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models.

Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

3 code implementations CVPR 2020 Vincent Le Guen, Nicolas Thome

Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods.

Disentanglement Video Prediction +1

Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models

3 code implementations NeurIPS 2019 Vincent Le Guen, Nicolas Thome

We introduce a differentiable loss function suitable for training deep neural nets, and provide a custom back-prop implementation for speeding up optimization.

Change Detection Dynamic Time Warping +3

DualDis: Dual-Branch Disentangling with Adversarial Learning

1 code implementation3 Jun 2019 Thomas Robert, Nicolas Thome, Matthieu Cord

To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for class and attribute information respectively.

Attribute Data Augmentation +3

BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

1 code implementation31 Jan 2019 Hedi Ben-Younes, Rémi Cadene, Nicolas Thome, Matthieu Cord

We demonstrate the practical interest of our fusion model by using BLOCK for two challenging tasks: Visual Question Answering (VQA) and Visual Relationship Detection (VRD), where we design end-to-end learnable architectures for representing relevant interactions between modalities.

Question Answering Relationship Detection +4

HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning

no code implementations ECCV 2018 Thomas Robert, Nicolas Thome, Matthieu Cord

In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet.

Classification Decoder +2

Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings

1 code implementation30 Apr 2018 Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Nicolas Thome, Matthieu Cord

Designing powerful tools that support cooking activities has rapidly gained popularity due to the massive amounts of available data, as well as recent advances in machine learning that are capable of analyzing them.

BIG-bench Machine Learning Cross-Modal Retrieval +1

Deformable Part-based Fully Convolutional Network for Object Detection

no code implementations19 Jul 2017 Taylor Mordan, Nicolas Thome, Matthieu Cord, Gilles Henaff

Existing region-based object detectors are limited to regions with fixed box geometry to represent objects, even if those are highly non-rectangular.

Object object-detection +1

Gossip training for deep learning

1 code implementation29 Nov 2016 Michael Blot, David Picard, Matthieu Cord, Nicolas Thome

We address the issue of speeding up the training of convolutional networks.

Deep Learning

Maxmin convolutional neural networks for image classification

no code implementations25 Oct 2016 Michael Blot, Matthieu Cord, Nicolas Thome

Convolutional neural networks (CNN) are widely used in computer vision, especially in image classification.

Classification General Classification +2

Master's Thesis : Deep Learning for Visual Recognition

1 code implementation18 Oct 2016 Rémi Cadène, Nicolas Thome, Matthieu Cord

Our last contribution is a framework, build on top of Torch7, for training and testing deep models on any visual recognition tasks and on datasets of any scale.

Deep Learning Weakly-supervised Learning

Deep Neural Networks Under Stress

1 code implementation11 May 2016 Micael Carvalho, Matthieu Cord, Sandra Avila, Nicolas Thome, Eduardo Valle

In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets.

Transfer Learning

Fantope Regularization in Metric Learning

no code implementations CVPR 2014 Marc T. Law, Nicolas Thome, Matthieu Cord

This paper introduces a regularization method to explicitly control the rank of a learned symmetric positive semidefinite distance matrix in distance metric learning.

Face Verification General Classification +2

Top-Down Regularization of Deep Belief Networks

no code implementations NeurIPS 2013 Hanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim

We suggest a deep learning strategy that bridges the gap between the two phases, resulting in a three-phase learning procedure.

Object Recognition

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