Etienne Meunier

Open intern position at IPSL working on diffusion models for ocean model emulation : Offer

I am a Postdoc at CNRS / IPSL in Paris, working on deep learning approaches for ocean modeling. My PhD focused on unsupervised training of neural networks for motion analysis. I was part of the Serpico team, led by Charles Kervrann. My PhD advisor was Patrick Bouthemy.

From 2019 to 2020, I worked as a visiting scholar at University British Columbia in Mostafavi Lab working on deep learning approach to interpret genomics data.

I hold a Master's degree in Computer Science from Boston University and a "Diplôme d’ingénieur" (MS) from ECE Paris. At Boston University I worked on a research project on predicting energy consumption from historical data with Eugene Pinsky. During my study, I also worked as a freelance researcher developping a shark detection algorithm for the CSR in La Reunion Island.

My interests lie in unsupervised deep learning applications, particularly in diverse signal processing areas. Moreover, I am enthusiastic about exploring novel research domains. I have a strong background in computer science and mathematics related to machine learning. Additionally, I am proficient in writing functional software and understanding cutting-edge papers in computer vision. Being curious and hard-working, I am eager to immerse myself in exploring new subjects.

etienne.meunier@inria.fr  /  CV  /  Phd-Manuscript  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research

My current work focuses on computer vision, machine learning, video analysis and unsupervised learning.

project image Hover Image

Unsupervised motion segmentation in one go: Smooth long-term model over a video


Etienne Meunier and Patrick Bouthemy
ArXiv, 2023
arxiv /

We learn to perform motion segmentation over a video sequence in a single pass in a fully unsupervised manner, using a long-term spatio-temporal model based on splines. The method is very fast at test time and provides temporally consistent labels.
project image Hover Image

Unsupervised space-time network for temporally-consistent segmentation of multiple motions


Etienne Meunier and Patrick Bouthemy
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
paper / video / code /

We extend unsupervised motion segmentation to longer sequences by leveraging spatio-temporal motion models and 3D networks. Provide consistent labels accros the video and improves network robustness to erroneous optical flow.
project image Hover Image

EM-driven unsupervised learning for motion segmentation


Etienne Meunier, Anaïs Badoual and Patrick Bouthemy
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2023
paper / arxiv / code /

We introduce a loss function theoretically grounded in the expectation maximisation framework to train networks to segment optical flow fields without any ground truth labels. Easy to set-up, robust to errors and computationally cheap, it can also be used as a regularisation term for any video segmentation project.
project image Hover Image

Unsupervised computation of salient motion maps from the interpretation of a frame- based classification network


Etienne Meunier and Patrick Bouthemy
British Machine Vision Conference (BMVC) , 2021
paper / video /

We detect motion saliency in videos using a weakly-supervised approach based on the gradient-based interpretation of a classification network. Applications on handheld camera videos to distinguish parallax from independent motion and on crowd videos for anomaly motion detection.
project image Hover Image

Interpreting deep learning models in genomics using genetic algorithm


Etienne Meunier, Gherman Novakovsky and Sara Mostafavi
Machine Learning in Computational Biology 2019 (MLCB), 2019

We developed a genetic algorithm to generate diverse DNA sequences that maximize the CNN model’s output, which predicts the cell type specificity of accessible DNA regions. Our tool provide a fast way to extract motifs specific to a given cell type and the results show biological relevance.

Other Projects

These include coursework, side projects, and research work that has not been published.

project image

Shark detection


Consulting
2019-10-01

We designed a functional shark detection pipeline that combines deep learning techniques for underwater image-based shark detection and an adversarial framework for domain adaptation. The pipeline incorporates a network of real-time underwater cameras, enabling efficient shark detection and immediate communication of alerts to on-ground sites. The pipeline is undergoing testing by the CSR in La Reunion Island.
project image

Micropolis GAN


BU Advanced Machine Learning and Neural Networks
2019-09-01
code /

We trained a GAN to generate city structures within the virtual environment of the game “Micropolis.” Our primary objective was to evaluate the generator’s ability to produce city layouts that adhere to the game’s specific requirements. To gauge the effectiveness of the generator, we compared the cities it generated with those obtained through a genetic algorithm that was guided by the game’s scoring function.

Design and source code from Jon Barron's website.