Moritz Böhle

I am a post doc researcher at Kyutai in Paris. Before that, I did a PhD at the Computer Vision and Machine Learning group at the Max Planck Institute for Informatics in Saarbrücken, Germany, where I was advised by Prof. Bernt Schiele and Prof. Mario Fritz. My research is focused on interpretable, trustworthy, and responsible deep learning. Before commencing my doctoral studies, I obtained a Bachelor’s degree in Physics at the Free University in Berlin, Germany, in 2016 and a Master’s degree at the Bernstein Center for Computational Neuroscience in Berlin, Germany, in 2019.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Publications
B-cosification



B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Shreyash Arya*, Sukrut Rao*, Moritz Böhle*, Bernt Schiele
(*equal contribution)
NeurIPS, 2024

Paper | Code

Qualitative Result Example



Discover-then-name: Task-agnostic Concept Bottlenecks via Automated Concept Discovery
Sweta Mahajan*, Sukrut Rao*, Moritz Böhle, Bernt Schiele
(*equal contribution)
ECCV, 2024

Paper | Code | Video | Slides

Good Teachers Explain

Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
Amin Parchami-Araghi*, Moritz Böhle*, Sukrut Rao*, Bernt Schiele
(*equal contribution)
ECCV, 2024

Paper | Code

B-cos explanation

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele
TPAMI, 2024

Paper | Code |
Talk @ MIT Vision & Graphics Seminar | Talk @ XAI4CV Workshop

Temperature

Better Understanding Differences in Attribution Methods via Systematic Evaluations
Sukrut Rao, Moritz Böhle, Bernt Schiele
TPAMI, 2024

Paper | Code | Video

Temperature

Studying How to Efficiently and Effectively Guide Models with Explanations.
Sukrut Rao*, Moritz Böhle*, Amin Parchami-Araghi, Bernt Schiele
(*equal contribution)
ICCV, 2023

Paper | Code | Video

Temperature

Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data
Anna Kukleva*, Moritz Böhle*, Bernt Schiele, Hilde Kuehne, Christian Rupprecht
(*equal contribution)
ICLR, 2023

Paper | Code

B-cos explanation

B-cos Networks: Alignment is All We Need for Interpretability
Moritz Böhle, Mario Fritz, Bernt Schiele
CVPR, 2022

Paper | Code |
Talk @ MIT Vision & Graphics Seminar | Talk @ XAI4CV Workshop

Temperature

Towards Better Understanding Attribution Methods
Sukrut Rao, Moritz Böhle, Bernt Schiele
CVPR, 2022

Paper | Code | Video

CoDA Explanation

Optimising for Interpretability: Convolutional Dynamic Alignment Networks
Moritz Böhle, Mario Fritz, Bernt Schiele
TPAMI, 2022

Paper | Code | Video

CoDA Explanation

Convolutional Dynamic Alignment Networks for Interpretable Classifications
Moritz Böhle, Mario Fritz, Bernt Schiele
CVPR (oral), 2021

Paper | Code | Video

LRP for AD Patient

Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
Moritz Böhle*, Fabian Eitel*, Martin Weygandt, Kerstin Ritter
(*equal contribution)
Frontiers in Aging Neuroscience, 2019

Paper | Code


Talks & Academic Activities

I am further proud to have served as a reviewer for IEEE PAMI, CVPR, ECCV, ICLR, NeurIPS, IEEE Trans. Inf. Forensics Secur., and ICML, and happy to have been named an outstanding reviewer for ECCV 2022!


Template stolen from Anna Kukleva who stole from Jon Barron :) Big thanks!