Mathieu Salzmann
EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne
+41 21 693 81 92
EPFL › VPS › SDSC › SDSC-GE
Website: https://www.datascience.ch
EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne
+41 21 693 81 92
EPFL › IC › IINFCOM › CVLAB
Website: https://cvlab.epfl.ch/
EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne
+41 21 693 81 92
EPFL › IC › IC-SIN › SIN-ENS
Website: https://sin.epfl.ch
EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne
+41 21 693 81 92
EPFL › CDH › CDH-SODH › SODH-ENS
EPFL SDSC
INN 218 (Bâtiment INN)
Station 14
1015 Lausanne
+41 21 693 81 92
EPFL › IC › IC-SSC › SSC-ENS
Website: https://ssc.epfl.ch
Expertise
Machine Learning
Current work
- Deep learning for 2D and 3D visual scene understanding
- Efficient and robust deep learning
- Domain adaptation and generalization
- Interpretable machine learning
News
- 4 papers accepted to ECCV 2024
- 1 paper accepted (oral) to ACM MM 2024
- 1 paper accepted to BMVC 2024
- 1 paper accepted to ICML 2024
- 3 papers accepted to ICLR 2024
- 6 papers accepted to CVPR 2024
- Our work in collaboration with S. Süsstrunk and R. Baroni on comics reconfiguration was displayed at the EPFL Pavilion A
- 1 paper accepted to NeurIPS 2023
- 5 papers accepted to ICCV 2023
- 1 paper accepted to ICML 2023
- I am Area Chair for ICML 2023, CVPR 2023, ICCV 2023, NeurIPS 2023, AAAI 2024, ECCV 2024
- I am Action Editor for TMLR
- I am Associate Editor for IEEE TPAMI
- As of Sept 2019, I have a Courtesy Appointment with the EPFL College of Humanities
Teaching & PhD
PhD Students
Zhuoqian Yang, Haoqi Wang, Yann Bouquet, Tianzong Zhang, Malo Lucas Perez, Saqib Javed, Megh Shukla, Shuangqi Li, Liying Lu, Pierre Victor Ancey
Past EPFL PhD Students
Past EPFL PhD Students as codirector
Kaicheng Yu, Isinsu Katircioglu, Chen Liu, Jan Bednarík, Krishna Kanth Nakka, Shuxuan Guo, Vidit Vidit, Sena Kiciroglu, Krzysztof Maciej Lis, Deblina Bhattacharjee, Davydov Andrey
Courses
Introduction to machine learning
CS-233
Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.