We worked on generic image collection analysis, focussing on interpretability and looking at problems like clustering or unsupervised image decomposition. The Deep Transformation Invariant approach we developed is one of the idea at the core of the new ERC DISCOVER project. We developed proof of concepts of its application to many problems, and in particular paleographic analysis.
Publications
Deep Transformation-Invariant Clustering
T. Monnier, T. Groueix, M. Aubry
NeurIPS 2020
Download pdf | View project web page
Unsupervised Layered Image Decomposition into Object Prototypes
T. Monnier, E. Vincent, J. Ponce, M. Aubry
ICCV 2021
Download pdf | View project web page
The Learnable Typewriter A Generative Approach to Text Line Analysis
Y. Siglidis, N. Gonthier, J. Gaubil, T. Monnier, M. Aubry
ArXiv 2023
Download pdf | View project web page