Tom Monnier

Tom Monnier

PhD student at Imagine - ENPC

6-8 Av Blaise Pascal - Cité Descartes
77455 Marne-la-Vallée, France

Email: tom dot monnier at enpc dot fr

I am a second-year PhD student in the Imagine research group at École des Ponts ParisTech (ENPC) under the supervision of Mathieu Aubry. Before that, I received my engineering degree in mathematics and computer science from Mines ParisTech in 2019.

I am interested in computer vision, machine learning and deep learning. My research currently focuses on solving computer vision tasks without manual annotations, through automatically generated data, self-supervised learning techniques or unsupervised algorithms.

News

Show more Hide

09 / 2021 Our paper "Representing Shape Collections with Alignment-Aware Linear Models" is published on arxiv
07 / 2021 Our sprite-based image decomposition approach has been accepted to ICCV 2021!
05 / 2021 Starting a remote internship in the Creative Intelligence Lab at Adobe Research
04 / 2021 Our paper "Unsupervised Layered Image Decomposition into Object Prototypes" is published on arxiv
12 / 2020 Presenting DTI-Clustering at a workshop for ParisMLGroup
11 / 2020 Presenting docExtractor at a DHNord 2020 workshop
10 / 2020 Our work on DTI-Clustering is accepted at NeurIPS 2020 as an oral presentation!
06 / 2020 Our paper "Deep Transformation-Invariant Clustering" is published on arxiv
06 / 2020 Our paper "docExtractor: An off-the-shelf historical document element extraction" is accepted at ICFHR 2020 as an oral!
02 / 2020 Starting PhD in the Imagine research group at ENPC under the supervision of Mathieu Aubry
01 / 2020 Our web application for watermark recognition is online, check out the paper and test the app here!

Publications

Representing Shape Collections with Alignment-Aware Linear Models
Romain Loiseau, Tom Monnier, Mathieu Aubry, Loïc Landrieu
arXiv 2021
paper | webpage | code | bibtex

We characterize 3D shapes as affine transformations of linear families learned without supervision, and showcase its advantages on large shape collections.

Unsupervised Layered Image Decomposition into Object Prototypes
Tom Monnier, Elliot Vincent, Jean Ponce, Mathieu Aubry
ICCV 2021
paper | webpage | code | video | slides | bibtex

An unsupervised learning framework to decompose images into object layers modeled as transformed instances of prototypical images called sprites.

Deep Transformation-Invariant Clustering
Tom Monnier, Thibault Groueix, Mathieu Aubry
NeurIPS 2020 (oral presentation)
paper | webpage | code | video | slides | bibtex

A simple and interpretable approach to clustering that jointly learns prototypes and prototype transformations to match data.

docExtractor: An off-the-shelf historical document element extraction
Tom Monnier, Mathieu Aubry
ICFHR 2020 (oral presentation)
paper | webpage | code | demo | video | slides | bibtex

Leveraging synthetic data and segmentation networks for generic element extraction in real historical document images.

A web application for watermark recognition
O. Bounou, T. Monnier, I. Pastrolin, X. Shen, C. Bénévent and others
JDMDH 2020
paper | web application | related paper (Shen et al.)

New public web application dedicated to automatic watermark recognition.

Teaching

Winter 2020 Deep Learning (DEEPL), Teacher Assistant, Master level, ENPC

Work experience

05 / 2021 - 08 / 2021 Research intern in the Creative Intelligence Lab at Adobe Research, supervised by Matt Fisher
09 / 2019 - 01 / 2020 Research engineer at École Nationale des Chartes
04 / 2019 - 08 / 2019 Research intern in computer vision at ENPC, advised by Mathieu Aubry
11 / 2018 - 03 / 2019 Data scientist at Tinyclues in Paris (part-time)
01 / 2018 - 07 / 2018 Data science intern at Tinyclues in Paris, supervised by Andrey Krivonogov and Artem Kozhevnikov
07 / 2017 - 12 / 2017 Research intern in biostatistics at MSKCC in New York, advised by Matahi Moarii and Elli Papaemmanuil
09 / 2016 - 03 / 2017 Research intern in game theory at Université Paris-Dauphine, advised by Guillaume Vigeral and Miquel Oliu-Barton

© You are welcome to copy this website's code for your personal use, please attribute the source with a link back to this page and remove analytics in the header.
This template is inspired from great websites I like such as this one or this one.

Last update: September 2021