Search Results for author: David Picard

Found 43 papers, 16 papers with code

Analysis of Classifier-Free Guidance Weight Schedulers

no code implementations19 Apr 2024 Xi Wang, Nicolas Dufour, Nefeli Andreou, Marie-Paule Cani, Victoria Fernandez Abrevaya, David Picard, Vicky Kalogeiton

Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models.

Multiple Locally Linear Kernel Machines

no code implementations17 Jan 2024 David Picard

In this paper we propose a new non-linear classifier based on a combination of locally linear classifiers.

Image Compression using only Attention based Neural Networks

no code implementations17 Oct 2023 Natacha Luka, Romain Negrel, David Picard

In recent research, Learned Image Compression has gained prominence for its capacity to outperform traditional handcrafted pipelines, especially at low bit-rates.

Image Compression Quantization

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning

no code implementations22 Aug 2023 Grégoire Petit, Michael Soumm, Eva Feillet, Adrian Popescu, Bertrand Delezoide, David Picard, Céline Hudelot

Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.

Class Incremental Learning Incremental Learning

LRVS-Fashion: Extending Visual Search with Referring Instructions

2 code implementations5 Jun 2023 Simon Lepage, Jérémie Mary, David Picard

This paper introduces a new challenge for image similarity search in the context of fashion, addressing the inherent ambiguity in this domain stemming from complex images.

Contrastive Learning Image Similarity Search +2

Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search

no code implementations1 Feb 2023 Marie-Morgane Paumard, Hedi Tabia, David Picard

Solving jigsaw puzzles requires to grasp the visual features of a sequence of patches and to explore efficiently a solution space that grows exponentially with the sequence length.

Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?

no code implementations20 Dec 2022 Monika Wysoczańska, Tom Monnier, Tomasz Trzciński, David Picard

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks.

Question Answering Representation Learning +2

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

1 code implementation ICCV 2023 Yue Zhu, Nermin Samet, David Picard

We also propose three tasks: i) 3D whole-body pose lifting from 2D complete whole-body pose, ii) 3D whole-body pose lifting from 2D incomplete whole-body pose, and iii) 3D whole-body pose estimation from a single RGB image.

3D Facial Landmark Localization 3D Hand Pose Estimation +1

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

1 code implementation10 Oct 2022 Nicolas Dufour, David Picard, Vicky Kalogeiton

In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details.

Pose Transfer Reconstruction +1

Decanus to Legatus: Synthetic training for 2D-3D human pose lifting

1 code implementation5 Oct 2022 Yue Zhu, David Picard

3D human pose estimation is a challenging task because of the difficulty to acquire ground-truth data outside of controlled environments.

3D Human Pose Estimation 3D Pose Estimation

PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning

no code implementations14 Sep 2022 Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard, Bertrand Delezoide

Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state.

Class Incremental Learning Incremental Learning +1

Unveiling the Latent Space Geometry of Push-Forward Generative Models

no code implementations21 Jul 2022 Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard

We investigate the relationship between the performance of these models and the geometry of their latent space.

Face Model

Instance-Aware Observer Network for Out-of-Distribution Object Segmentation

no code implementations18 Jul 2022 Victor Besnier, Andrei Bursuc, David Picard, Alexandre Briot

To address this issue, we build upon the recent ObsNet approach by providing object instance knowledge to the observer.

Object Out of Distribution (OOD) Detection +1

EdiBERT, a generative model for image editing

1 code implementation30 Nov 2021 Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary, David Picard

Advances in computer vision are pushing the limits of im-age manipulation, with generative models sampling detailed images on various tasks.

Image Denoising Image Manipulation

Non asymptotic bounds in asynchronous sum-weight gossip protocols

no code implementations19 Nov 2021 David Picard, Jérôme Fellus, Stéphane Garnier

This paper focuses on non-asymptotic diffusion time in asynchronous gossip protocols.

Latent reweighting, an almost free improvement for GANs

no code implementations19 Oct 2021 Thibaut Issenhuth, Ugo Tanielian, David Picard, Jeremie Mary

Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting different classes of images.

Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

2 code implementations16 Sep 2021 David Picard

In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision.

Image Collation: Matching illustrations in manuscripts

no code implementations18 Aug 2021 Ryad Kaoua, Xi Shen, Alexandra Durr, Stavros Lazaris, David Picard, Mathieu Aubry

For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

no code implementations28 May 2021 Victor Besnier, David Picard, Alexandre Briot

In this paper, we show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving, by triggering a fallback behavior if a target accuracy cannot be guaranteed.

Autonomous Driving Image Segmentation +1

Deep Learning Based Detection for Spectrally Efficient FDM Systems

no code implementations21 Mar 2021 David Picard, Arsenia Chorti

In this study we present how to approach the problem of building efficient detectors for spectrally efficient frequency division multiplexing (SEFDM) systems.

Rate Analysis and Deep Neural Network Detectors for SEFDM FTN Systems

no code implementations3 Mar 2021 Arsenia Chorti, David Picard

In this work we compare the capacity and achievable rate of uncoded faster than Nyquist (FTN) signalling in the frequency domain, also referred to as spectrally efficient FDM (SEFDM).

Learning Disconnected Manifolds: Avoiding The No Gan's Land by Latent Rejection

no code implementations1 Jan 2021 Thibaut Issenhuth, Ugo Tanielian, David Picard, Jeremie Mary

Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting disconnected manifolds.

SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression

no code implementations4 Sep 2020 Diogo Luvizon, Hedi Tabia, David Picard

In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images.

3D Human Pose Estimation 3D Pose Estimation +1

Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimization

no code implementations26 May 2020 Marie-Morgane Paumard, David Picard, Hedi Tabia

We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions.

DIABLO: Dictionary-based Attention Block for Deep Metric Learning

no code implementations30 Apr 2020 Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein

Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks.

Metric Learning Representation Learning +1

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

1 code implementation15 Dec 2019 Diogo C. Luvizon, Hedi Tabia, David Picard

In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences.

3D Human Pose Estimation Action Recognition +1

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

1 code implementation ICCV 2019 Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein

Although the metric learning part is well addressed, this metric is usually computed over the average of the extracted deep features.

Ranked #18 on Metric Learning on CUB-200-2011 (using extra training data)

Image Retrieval Metric Learning +2

Leveraging Implicit Spatial Information in Global Features for Image Retrieval

no code implementations23 Jun 2018 Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein

Most image retrieval methods use global features that aggregate local distinctive patterns into a single representation.

Image Retrieval Retrieval

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

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.

Distributed Optimization

Human Pose Regression by Combining Indirect Part Detection and Contextual Information

1 code implementation6 Oct 2017 Diogo C. Luvizon, Hedi Tabia, David Picard

In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images.

Pose Estimation regression

Very Fast Kernel SVM under Budget Constraints

no code implementations31 Dec 2016 David Picard

In this paper we propose a fast online Kernel SVM algorithm under tight budget constraints.

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.

Covariance Descriptors for 3D Shape Matching and Retrieval

no code implementations CVPR 2014 Hedi Tabia, Hamid Laga, David Picard, Philippe-Henri Gosselin

We evaluate the performance of the proposed Bag of Covariance Matrices framework on 3D shape matching and retrieval applications and demonstrate its superiority compared to descriptor-based techniques.

Clustering Retrieval

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