Search Results for author: Stéphane Lathuilière

Found 41 papers, 20 papers with code

Mini but Mighty: Finetuning ViTs with Mini Adapters

1 code implementation7 Nov 2023 Imad Eddine Marouf, Enzo Tartaglione, Stéphane Lathuilière

Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning.

Transfer Learning

Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation

2 code implementations17 Oct 2023 Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière

Concretely, we propose "Test-Time Adaptation for Class-Incremental Learning" (TTACIL) that first fine-tunes Layer Norm parameters of the PTM on each test instance for learning task-specific features, and then resets them back to the base model to preserve stability.

Class Incremental Learning Incremental Learning +1

Face Aging via Diffusion-based Editing

no code implementations20 Sep 2023 Xiangyi Chen, Stéphane Lathuilière

We propose FADING, a novel approach to address Face Aging via DIffusion-based editiNG.

Face Age Editing

The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation

1 code implementation ICCV 2023 Giacomo Zara, Alessandro Conti, Subhankar Roy, Stéphane Lathuilière, Paolo Rota, Elisa Ricci

Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data.

Action Recognition Unsupervised Domain Adaptation

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

Test your samples jointly: Pseudo-reference for image quality evaluation

no code implementations7 Apr 2023 Marcelin Tworski, Stéphane Lathuilière

In this paper, we address the well-known image quality assessment problem but in contrast from existing approaches that predict image quality independently for every images, we propose to jointly model different images depicting the same content to improve the precision of quality estimation.

Image Quality Assessment Test

Few-shot Semantic Image Synthesis with Class Affinity Transfer

no code implementations CVPR 2023 Marlène Careil, Jakob Verbeek, Stéphane Lathuilière

The class affinity matrix is introduced as a first layer to the source model to make it compatible with the target label maps, and the source model is then further finetuned for the target domain.

Image Generation Semantic Segmentation

One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models

1 code implementation31 Mar 2023 Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière

Departing from the common notion of transferring only the target ``texture'' information, we leverage text-to-image diffusion models (e. g., Stable Diffusion) to generate a synthetic target dataset with photo-realistic images that not only faithfully depict the style of the target domain, but are also characterized by novel scenes in diverse contexts.

Data Augmentation One-shot Unsupervised Domain Adaptation +2

Plotting Behind the Scenes: Towards Learnable Game Engines

no code implementations23 Mar 2023 Willi Menapace, Aliaksandr Siarohin, Stéphane Lathuilière, Panos Achlioptas, Vladislav Golyanik, Elisa Ricci, Sergey Tulyakov

The key to learning such game AI is the exploitation of a large and diverse text corpus, collected in this work, describing detailed actions in a game and used to train our animation model.


Unifying conditional and unconditional semantic image synthesis with OCO-GAN

no code implementations25 Nov 2022 Marlène Careil, Stéphane Lathuilière, Camille Couprie, Jakob Verbeek

To allow for more control, image synthesis can be conditioned on semantic segmentation maps that instruct the generator the position of objects in the image.

Image Generation Semantic Segmentation

Autoregressive GAN for Semantic Unconditional Head Motion Generation

1 code implementation2 Nov 2022 Louis Airale, Xavier Alameda-Pineda, Stéphane Lathuilière, Dominique Vaufreydaz

In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose.

Talking Head Generation

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

1 code implementation4 Oct 2022 Yangsong Zhang, Subhankar Roy, Hongtao Lu, Elisa Ricci, Stéphane Lathuilière

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions.

Domain Adaptation Multi-target Domain Adaptation +2

Custom Structure Preservation in Face Aging

1 code implementation22 Jul 2022 Guillermo Gomez-Trenado, Stéphane Lathuilière, Pablo Mesejo, Óscar Cordón

In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image.

Face Age Editing

Online Unsupervised Domain Adaptation for Person Re-identification

no code implementations9 May 2022 Hamza Rami, Matthieu Ospici, Stéphane Lathuilière

Therefore, we present a new yet practical online setting for Unsupervised Domain Adaptation for person Re-ID with two main constraints: Online Adaptation and Privacy Protection.

Online unsupervised domain adaptation Person Re-Identification

Click to Move: Controlling Video Generation with Sparse Motion

1 code implementation ICCV 2021 Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri, Elisa Ricci, Stéphane Lathuilière

This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene.

Video Generation

HEMP: High-order Entropy Minimization for neural network comPression

no code implementations12 Jul 2021 Enzo Tartaglione, Stéphane Lathuilière, Attilio Fiandrotti, Marco Cagnazzo, Marco Grangetto

We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent.

Neural Network Compression Quantization +1

Ultra-low bitrate video conferencing using deep image animation

no code implementations1 Dec 2020 Goluck Konuko, Giuseppe Valenzise, Stéphane Lathuilière

In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications.

Image Animation Video Compression

DR2S : Deep Regression with Region Selection for Camera Quality Evaluation

no code implementations21 Sep 2020 Marcelin Tworski, Stéphane Lathuilière, Salim Belkarfa, Attilio Fiandrotti, Marco Cagnazzo

In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition.


Learning to Cluster under Domain Shift

1 code implementation ECCV 2020 Willi Menapace, Stéphane Lathuilière, Elisa Ricci

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i. e. labeled source data must be available.

Clustering Deep Clustering +1

Online Continual Learning under Extreme Memory Constraints

1 code implementation ECCV 2020 Enrico Fini, Stéphane Lathuilière, Enver Sangineto, Moin Nabi, Elisa Ricci

Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences.

Continual Learning

Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks

1 code implementation17 Sep 2019 Andrea Pilzer, Stéphane Lathuilière, Dan Xu, Mihai Marian Puscas, Elisa Ricci, Nicu Sebe

Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction.

Data Augmentation Depth Prediction +2

Budget-Aware Adapters for Multi-Domain Learning

no code implementations ICCV 2019 Rodrigo Berriel, Stéphane Lathuilière, Moin Nabi, Tassilo Klein, Thiago Oliveira-Santos, Nicu Sebe, Elisa Ricci

To implement this idea we derive specialized deep models for each domain by adapting a pre-trained architecture but, differently from other methods, we propose a novel strategy to automatically adjust the computational complexity of the network.

Attention-based Fusion for Multi-source Human Image Generation

no code implementations7 May 2019 Stéphane Lathuilière, Enver Sangineto, Aliaksandr Siarohin, Nicu Sebe

We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images.

Image Generation

Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

1 code implementation30 Apr 2019 Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto, Nicu Sebe

Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa.

Data Augmentation Image Generation +1

Online Adaptation through Meta-Learning for Stereo Depth Estimation

no code implementations17 Apr 2019 Zhen-Yu Zhang, Stéphane Lathuilière, Andrea Pilzer, Nicu Sebe, Elisa Ricci, Jian Yang

Our proposal is evaluated on the wellestablished KITTI dataset, where we show that our online method is competitive withstate of the art algorithms trained in a batch setting.

Meta-Learning Stereo Depth Estimation

Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation

no code implementations CVPR 2019 Andrea Pilzer, Stéphane Lathuilière, Nicu Sebe, Elisa Ricci

Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need of collecting ground-truth depth.

Depth Prediction Knowledge Distillation +2

Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View

no code implementations28 Feb 2019 Benoit Massé, Stéphane Lathuilière, Pablo Mesejo, Radu Horaud

In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video.

A Comprehensive Analysis of Deep Regression

2 code implementations22 Mar 2018 Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud

Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks.

Pose Estimation regression

Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction

no code implementations18 Nov 2017 Stéphane Lathuilière, Benoit Massé, Pablo Mesejo, Radu Horaud

Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision.

Q-Learning Reinforcement Learning (RL)

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