Théo Guesser

Théo Jaunet, Romain Vuillemot, Christian Wolf    


This work is at the crossroads of three different fields and explores techniques of data visualization to advance machine learning for robotics applications. We propose new techniques for the visualization of the sim2real gap, which provide insights into the difference in performance obtained when neural networks are applied out of distribution (OOD) in real settings. The objective is to pinpoint transfer problems and to assist researchers and engineers in the fields of machine learning for robotics to design neural models which better transfer to real world scenarios.

@inproceedings{Jaunet:2020,author = {Jaunet, Theo and Vuillemot, Romain and  Wolf, Christian},
title = {Theo guesser},
journal = {Proceedings of the Workshop on Visualization for AI explainability (VISxAI)},
year = {2020},
editors = {Mennatallah El-Assady, Duen Horng (Polo) Chau, Fred Hohman, Adam Perer, Hendrik Strobelt, Fernanda Viégas},
url = {}