About me

I am a research scientist of valeo.ai, an academic research lab focused on self-driving cars. Previously I have completed my PhD in 2018 at Université de Caen and ONERA under the supervision of Stéphane Herbin and Frédéric Jurie.

My research interests include machine learning that combine vision and language for better, lighter, clearer & safer automotive AI.

Publications

2019

DADA: Depth-aware Domain Adaptation in Semantic Segmentation

Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Mathieu Cord, Patrick Pérez.
Published in arxiv (pdf)

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Mathieu Cord, Patrick Pérez.
Computer Vision and Pattern Recognition, CVPR 2019 (pdf)

2018

Semantic bottleneck for computer vision tasks

Maxime Bucher, Stéphane Herbin, Frédéric Jurie.
Asian Conference on Computer Vision , ACCV 2018 (pdf)

Learning and exploitation of semantic representations for image classification and retrieval

Maxime Bucher.
Ph.D. thesis (pdf)

Zero-Shot Classification by Generating Artificial Visual Features

Maxime Bucher, Stéphane Herbin, Frédéric Jurie.
Reconnaissance des Formes, Image, Apprentissage et Perception , RFIAP 2018 (pdf)

2017

Generating visual representations for zero-shot classification

Maxime Bucher, Stéphane Herbin, Frédéric Jurie.
International Conference on Computer Vision Workshop, ICCV 2017 (pdf)

2016

Improving semantic embedding consistency by metric learning for zero-shot classiffication

Maxime Bucher, Stéphane Herbin, Frédéric Jurie.
European Conference on Computer Vision, ECCV 2016 (pdf)

Hard negative mining for metric learning based zero-shot classification

Maxime Bucher, Stéphane Herbin, Frédéric Jurie.
European Conference on Computer Vision Workshop, ECCV 2016 (pdf)