Search Results for author: Matthieu Cord

Found 134 papers, 83 papers with code

Skipping Computations in Multimodal LLMs

1 code implementation12 Oct 2024 Mustafa Shukor, Matthieu Cord

(2) Skipping computations during training can recover 97% of the original performance, even when skipping half of the blocks or removing 70% of the weights.

Question Answering Visual Question Answering

Annealed Winner-Takes-All for Motion Forecasting

1 code implementation17 Sep 2024 Yihong Xu, Victor Letzelter, Mickaël Chen, Éloi Zablocki, Matthieu Cord

Additionally, to compensate for limited performance, some approaches rely on training with a large set of hypotheses, requiring a post-selection step during inference to significantly reduce the number of predictions.

Motion Forecasting motion prediction +2

ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable

1 code implementation12 Sep 2024 Yuan Yin, Pegah Khayatan, Éloi Zablocki, Alexandre Boulch, Matthieu Cord

Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment.

Autonomous Driving

Valeo4Cast: A Modular Approach to End-to-End Forecasting

1 code implementation12 Jun 2024 Yihong Xu, Éloi Zablocki, Alexandre Boulch, Gilles Puy, Mickael Chen, Florent Bartoccioni, Nermin Samet, Oriane Siméoni, Spyros Gidaris, Tuan-Hung Vu, Andrei Bursuc, Eduardo Valle, Renaud Marlet, Matthieu Cord

In end-to-end forecasting, the model must jointly detect and track from sensor data (cameras or LiDARs) the past trajectories of the different elements of the scene and predict their future locations.

Motion Forecasting

Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs

1 code implementation26 May 2024 Mustafa Shukor, Matthieu Cord

Perceptual tokens (1) are easily distinguishable from textual ones inside LLMs, with significantly different representations, and complete translation to textual tokens does not exist.

What matters when building vision-language models?

no code implementations3 May 2024 Hugo Laurençon, Léo Tronchon, Matthieu Cord, Victor Sanh

The growing interest in vision-language models (VLMs) has been driven by improvements in large language models and vision transformers.

1 Image, 2*2 Stitching Image Retrieval +2

What Makes Multimodal In-Context Learning Work?

1 code implementation24 Apr 2024 Folco Bertini Baldassini, Mustafa Shukor, Matthieu Cord, Laure Soulier, Benjamin Piwowarski

Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples.

In-Context Learning

Mind-to-Image: Projecting Visual Mental Imagination of the Brain from fMRI

no code implementations8 Apr 2024 Hugo Caselles-Dupré, Charles Mellerio, Paul Hérent, Alizée Lopez-Persem, Benoit Béranger, Mathieu Soularue, Pierre Fautrel, Gauthier Vernier, Matthieu Cord

The reconstruction of images observed by subjects from fMRI data collected during visual stimuli has made strong progress in the past decade, thanks to the availability of extensive fMRI datasets and advancements in generative models for image generation.

Image Generation

FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models

no code implementations29 Mar 2024 Barbara Toniella Corradini, Mustafa Shukor, Paul Couairon, Guillaume Couairon, Franco Scarselli, Matthieu Cord

The pipeline is as follows: the image is passed to both a captioner model (i. e. BLIP) and a diffusion model (i. e., Stable Diffusion Model) to generate a text description and visual representation, respectively.

Image Generation Image Segmentation +3

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

1 code implementation22 Mar 2024 Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor, Éloi Zablocki, Matthieu Cord, Alexandre Alahi

Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored.

 Ranked #1 on Trajectory Prediction on nuScenes (using extra training data)

Diversity Trajectory Prediction

Improved Baselines for Data-efficient Perceptual Augmentation of LLMs

no code implementations20 Mar 2024 Théophane Vallaeys, Mustafa Shukor, Matthieu Cord, Jakob Verbeek

The abilities of large language models (LLMs) have recently progressed to unprecedented levels, paving the way to novel applications in a wide variety of areas.

Audio captioning Image Captioning +2

PointBeV: A Sparse Approach for BeV Predictions

1 code implementation CVPR 2024 Loick Chambon, Eloi Zablocki, Mickaël Chen, Florent Bartoccioni, Patrick Pérez, Matthieu Cord

To address this we propose PointBeV a novel sparse BeV segmentation model operating on sparse BeV cells instead of dense grids.

Manipulating Trajectory Prediction with Backdoors

no code implementations21 Dec 2023 Kaouther Messaoud, Kathrin Grosse, Mickael Chen, Matthieu Cord, Patrick Pérez, Alexandre Alahi

In this paper, we focus on backdoors - a security threat acknowledged in other fields but so far overlooked for trajectory prediction.

Autonomous Vehicles Trajectory Prediction

Reliability in Semantic Segmentation: Can We Use Synthetic Data?

1 code implementation14 Dec 2023 Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord

Assessing the robustness of perception models to covariate shifts and their ability to detect out-of-distribution (OOD) inputs is crucial for safety-critical applications such as autonomous vehicles.

Autonomous Vehicles Out of Distribution (OOD) Detection +1

ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation

no code implementations11 Dec 2023 Cédric Rommel, Victor Letzelter, Nermin Samet, Renaud Marlet, Matthieu Cord, Patrick Pérez, Eduardo Valle

Monocular 3D human pose estimation (3D-HPE) is an inherently ambiguous task, as a 2D pose in an image might originate from different possible 3D poses.

Monocular 3D Human Pose Estimation regression

PointBeV: A Sparse Approach to BeV Predictions

1 code implementation1 Dec 2023 Loick Chambon, Eloi Zablocki, Mickael Chen, Florent Bartoccioni, Patrick Perez, Matthieu Cord

To address this, we propose PointBeV, a novel sparse BeV segmentation model operating on sparse BeV cells instead of dense grids.

Bird's-Eye View Semantic Segmentation

ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge

no code implementations24 Nov 2023 Eslam Abdelrahman, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord, Patrick Perez, Mohamed Elhoseiny

Diffusion models break down the challenging task of generating data from high-dimensional distributions into a series of easier denoising steps.

Denoising Image Generation

Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning

1 code implementation1 Oct 2023 Mustafa Shukor, Alexandre Rame, Corentin Dancette, Matthieu Cord

Based on our ICL study, (3) we push ICL further and propose new multimodal ICL variants such as; Multitask-ICL, Chain-of-Hindsight-ICL, and Self-Correcting-ICL.

In-Context Learning Instruction Following +1

Gradpaint: Gradient-Guided Inpainting with Diffusion Models

no code implementations18 Sep 2023 Asya Grechka, Guillaume Couairon, Matthieu Cord

For the specific task of image inpainting, the current guiding mechanism relies on copying-and-pasting the known regions from the input image at each denoising step.

Denoising Image Inpainting +1

DiffHPE: Robust, Coherent 3D Human Pose Lifting with Diffusion

no code implementations4 Sep 2023 Cédric Rommel, Eduardo Valle, Mickaël Chen, Souhaiel Khalfaoui, Renaud Marlet, Matthieu Cord, Patrick Pérez

We present an innovative approach to 3D Human Pose Estimation (3D-HPE) by integrating cutting-edge diffusion models, which have revolutionized diverse fields, but are relatively unexplored in 3D-HPE.

3D Human Pose Estimation

UnIVAL: Unified Model for Image, Video, Audio and Language Tasks

1 code implementation30 Jul 2023 Mustafa Shukor, Corentin Dancette, Alexandre Rame, Matthieu Cord

Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning.

Out-of-Distribution Generalization

Zero-shot spatial layout conditioning for text-to-image diffusion models

no code implementations ICCV 2023 Guillaume Couairon, Marlène Careil, Matthieu Cord, Stéphane Lathuilière, Jakob Verbeek

Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling and allow for an intuitive and powerful user interface to drive the image generation process.

Image Generation Segmentation +1

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

1 code implementation NeurIPS 2023 Hugo Laurençon, Lucile Saulnier, Léo Tronchon, Stas Bekman, Amanpreet Singh, Anton Lozhkov, Thomas Wang, Siddharth Karamcheti, Alexander M. Rush, Douwe Kiela, Matthieu Cord, Victor Sanh

Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks.

Ranked #14 on MMR total on MRR-Benchmark (using extra training data)

MMR total

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

1 code implementation15 Jun 2023 Yihong Xu, Loïck Chambon, Éloi Zablocki, Mickaël Chen, Alexandre Alahi, Matthieu Cord, Patrick Pérez

In fact, conventional forecasting methods are usually not trained nor tested in real-world pipelines (e. g., with upstream detection, tracking, and mapping modules).

Benchmarking Motion Forecasting

eP-ALM: Efficient Perceptual Augmentation of Language Models

1 code implementation ICCV 2023 Mustafa Shukor, Corentin Dancette, Matthieu Cord

In this work, we propose to rather direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception.

In-Context Learning Visual Question Answering (VQA)

PowerQuant: Automorphism Search for Non-Uniform Quantization

no code implementations24 Jan 2023 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

In this paper, we identity the uniformity of the quantization operator as a limitation of existing approaches, and propose a data-free non-uniform method.

Quantization

Co-Training 2L Submodels for Visual Recognition

1 code implementation CVPR 2023 Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou

Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, "submodels", with stochastic depth: i. e. activating only a subset of the layers and skipping others.

Image Classification Semantic Segmentation

Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

1 code implementation20 Dec 2022 Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, David Lopez-Paz

In this paper, we thus propose model ratatouille, a new strategy to recycle the multiple fine-tunings of the same foundation model on diverse auxiliary tasks.

Diversity Domain Generalization +1

Co-training $2^L$ Submodels for Visual Recognition

1 code implementation9 Dec 2022 Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth.

Image Classification 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

OCTET: Object-aware Counterfactual Explanations

1 code implementation CVPR 2023 Mehdi Zemni, Mickaël Chen, Éloi Zablocki, Hédi Ben-Younes, Patrick Pérez, Matthieu Cord

We conduct a set of experiments on counterfactual explanation benchmarks for driving scenes, and we show that our method can be adapted beyond classification, e. g., to explain semantic segmentation models.

Autonomous Driving counterfactual +4

DiffEdit: Diffusion-based semantic image editing with mask guidance

4 code implementations20 Oct 2022 Guillaume Couairon, Jakob Verbeek, Holger Schwenk, Matthieu Cord

Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image.

Image Generation

SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance

no code implementations8 Jul 2022 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks.

Dynamic Query Selection for Fast Visual Perceiver

no code implementations22 May 2022 Corentin Dancette, Matthieu Cord

Transformers have been matching deep convolutional networks for vision architectures in recent works.

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

Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation

1 code implementation25 Apr 2022 Antoine Saporta, Arthur Douillard, Tuan-Hung Vu, Patrick Pérez, Matthieu Cord

Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain.

Continual Learning Semantic Segmentation +2

Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval

1 code implementation20 Apr 2022 Mustafa Shukor, Guillaume Couairon, Asya Grechka, Matthieu Cord

We propose a new retrieval framework, T-Food (Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval) that exploits the interaction between modalities in a novel regularization scheme, while using only unimodal encoders at test time for efficient retrieval.

Cross-Modal Retrieval Retrieval +1

DeiT III: Revenge of the ViT

11 code implementations14 Apr 2022 Hugo Touvron, Matthieu Cord, Hervé Jégou

Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT.

 Ranked #1 on Image Classification on ImageNet ReaL (Number of params metric)

Data Augmentation Image Classification +3

SPIQ: Data-Free Per-Channel Static Input Quantization

no code implementations28 Mar 2022 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

Computationally expensive neural networks are ubiquitous in computer vision and solutions for efficient inference have drawn a growing attention in the machine learning community.

Data Free Quantization object-detection +2

Three things everyone should know about Vision Transformers

7 code implementations18 Mar 2022 Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Verbeek, Hervé Jégou

(2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks.

Ranked #9 on Image Classification on CIFAR-10 (using extra training data)

Fine-Grained Image Classification

FlexIT: Towards Flexible Semantic Image Translation

1 code implementation CVPR 2022 Guillaume Couairon, Asya Grechka, Jakob Verbeek, Holger Schwenk, Matthieu Cord

Via the latent space of an auto-encoder, we iteratively transform the input image toward the target point, ensuring coherence and quality with a variety of novel regularization terms.

Image Generation Translation

CSG0: Continual Urban Scene Generation with Zero Forgetting

no code implementations6 Dec 2021 Himalaya Jain, Tuan-Hung Vu, Patrick Pérez, Matthieu Cord

With the rapid advances in generative adversarial networks (GANs), the visual quality of synthesised scenes keeps improving, including for complex urban scenes with applications to automated driving.

Continual Learning Scene Generation +1

RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks

no code implementations NeurIPS 2021 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

Deep Neural Networks (DNNs) are ubiquitous in today's computer vision landscape, despite involving considerable computational costs.

STEEX: Steering Counterfactual Explanations with Semantics

1 code implementation17 Nov 2021 Paul Jacob, Éloi Zablocki, Hédi Ben-Younes, Mickaël Chen, Patrick Pérez, Matthieu Cord

In this work, we address the problem of producing counterfactual explanations for high-quality images and complex scenes.

counterfactual Counterfactual Explanation

RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging

no code implementations30 Sep 2021 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration.

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.

Raising context awareness in motion forecasting

1 code implementation16 Sep 2021 Hédi Ben-Younes, Éloi Zablocki, Mickaël Chen, Patrick Pérez, Matthieu Cord

Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history.

Motion Forecasting Trajectory Prediction

LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR

1 code implementation8 Sep 2021 Florent Bartoccioni, Éloi Zablocki, Patrick Pérez, Matthieu Cord, Karteek Alahari

In such a monocular setup, dense depth is obtained with either additional input from one or several expensive LiDARs, e. g., with 64 beams, or camera-only methods, which suffer from scale-ambiguity and infinite-depth problems.

Depth Completion Depth Estimation

Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization

2 code implementations7 Sep 2021 Alexandre Rame, Corentin Dancette, Matthieu Cord

In this paper, we introduce a new regularization - named Fishr - that enforces domain invariance in the space of the gradients of the loss: specifically, the domain-level variances of gradients are matched across training domains.

Domain Generalization Out-of-Distribution Generalization

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

1 code implementation ICCV 2021 Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time.

Segmentation Semantic Segmentation +2

Semantic Palette: Guiding Scene Generation with Class Proportions

1 code implementation CVPR 2021 Guillaume Le Moing, Tuan-Hung Vu, Himalaya Jain, Patrick Pérez, Matthieu Cord

Despite the recent progress of generative adversarial networks (GANs) at synthesizing photo-realistic images, producing complex urban scenes remains a challenging problem.

Data Augmentation Image Generation +1

RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks

no code implementations31 May 2021 Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs.

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

3 code implementations CVPR 2021 Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez

With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.

object-detection Object Detection +5

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

Driving Behavior Explanation with Multi-level Fusion

1 code implementation9 Dec 2020 Hédi Ben-Younes, Éloi Zablocki, Patrick Pérez, Matthieu Cord

In this era of active development of autonomous vehicles, it becomes crucial to provide driving systems with the capacity to explain their decisions.

Explainable artificial intelligence Trajectory Prediction

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

1 code implementation4 Dec 2020 Taylor Mordan, Matthieu Cord, Patrick Pérez, Alexandre Alahi

By increasing the number of attributes jointly learned, we highlight an issue related to the scales of gradients, which arises in MTL with numerous tasks.

Attribute Autonomous Driving +1

Powers of layers for image-to-image translation

no code implementations13 Aug 2020 Hugo Touvron, Matthijs Douze, Matthieu Cord, Hervé Jégou

We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc.

 Ranked #1 on Image-to-Image Translation on vangogh2photo (Frechet Inception Distance metric)

Deblurring Denoising +2

Insights from the Future for Continual Learning

1 code implementation24 Jun 2020 Arthur Douillard, Eduardo Valle, Charles Ollion, Thomas Robert, Matthieu Cord

Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting.

Class Incremental Learning Representation Learning +1

Overcoming Statistical Shortcuts for Open-ended Visual Counting

1 code implementation17 Jun 2020 Corentin Dancette, Remi Cadene, Xinlei Chen, Matthieu Cord

First, we propose the Modifying Count Distribution (MCD) protocol, which penalizes models that over-rely on statistical shortcuts.

ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

1 code implementation15 Jun 2020 Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance.

Self-Supervised Learning Semantic Segmentation +1

PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

2 code implementations ECCV 2020 Arthur Douillard, Matthieu Cord, Charles Ollion, Thomas Robert, Eduardo Valle

Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learning.

Class Incremental Learning Incremental Learning +1

Handling new target classes in semantic segmentation with domain adaptation

no code implementations2 Apr 2020 Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data distribution shift w. r. t.

Scene Segmentation Universal Domain Adaptation +2

Learning Representations by Predicting Bags of Visual Words

1 code implementation CVPR 2020 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.

Representation Learning

QUEST: Quantized embedding space for transferring knowledge

1 code implementation ECCV 2020 Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network.

Knowledge Distillation

This dataset does not exist: training models from generated images

no code implementations7 Nov 2019 Victor Besnier, Himalaya Jain, Andrei Bursuc, Matthieu Cord, Patrick Pérez

This naturally brings the question: Can we train a classifier only on the generated data?

REVE: Regularizing Deep Learning with Variational Entropy Bound

no code implementations15 Oct 2019 Antoine Saporta, Yifu Chen, Michael Blot, Matthieu Cord

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.

Deep Learning

Riemannian batch normalization for SPD neural networks

no code implementations NeurIPS 2019 Daniel Brooks, Olivier Schwander, Frederic Barbaresco, Jean-Yves Schneider, Matthieu Cord

Covariance matrices have attracted attention for machine learning applications due to their capacity to capture interesting structure in the data.

Action Recognition

Boosting Few-Shot Visual Learning with Self-Supervision

1 code implementation ICCV 2019 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.

Few-Shot Learning Self-Supervised Learning

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

SEMEDA: Enhancing Segmentation Precision with Semantic Edge Aware Loss

no code implementations6 May 2019 Yifu Chen, Arnaud Dapogny, Matthieu Cord

As a result, the predictions outputted by such networks usually struggle to accurately capture the object boundaries and exhibit holes inside the objects.

Edge Detection Segmentation +1

DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild

no code implementations ICCV 2019 Arnaud Dapogny, Kévin Bailly, Matthieu Cord

Face Alignment is an active computer vision domain, that consists in localizing a number of facial landmarks that vary across datasets.

Face Alignment

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

Images & Recipes: Retrieval in the cooking context

1 code implementation2 May 2018 Micael Carvalho, Rémi Cadène, David Picard, Laure Soulier, Matthieu Cord

Recent advances in the machine learning community allowed different use cases to emerge, as its association to domains like cooking which created the computational cuisine.

BIG-bench Machine Learning Retrieval

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

Finding beans in burgers: Deep semantic-visual embedding with localization

1 code implementation CVPR 2018 Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord

Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships.

Cross-Modal Retrieval Image Captioning +2

GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange

no code implementations4 Apr 2018 Michael Blot, David Picard, Matthieu Cord

We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent.

Deep Learning Distributed Optimization

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

Closed-Form Training of Mahalanobis Distance for Supervised Clustering

no code implementations CVPR 2016 Marc T. Law, Yao-Liang Yu, Matthieu Cord, Eric P. Xing

Clustering is the task of grouping a set of objects so that objects in the same cluster are more similar to each other than to those in other clusters.

Clustering Metric Learning +1

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.