World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
67
Citations
35570
World Ranking
2137
National Ranking
89

Overview

Matthias Bethge is affiliated with the University of Tübingen in Germany and has a research portfolio spanning computer science and health professions. Their work integrates multiple fields of study including artificial intelligence, computer vision and pattern recognition, cognitive neuroscience, and physical therapy, sports therapy, and rehabilitation.

The scientist has contributed extensively to research topics such as workplace health and well-being, medical practices and rehabilitation, visual attention and saliency detection, musculoskeletal pain and rehabilitation, domain adaptation and few-shot learning, health and medical studies, along with neural dynamics and brain function.

Frequent coauthors collaborating with Matthias Bethge include Wieland Brendel, Matthias Kümmerer, David Fauser, Thomas S. A. Wallis, and Wilfried Mau.

Their research has been published in multiple venues, with notable publication counts in arXiv (Cornell University), Die Rehabilitation, Zenodo (CERN European Organization for Nuclear Research), Journal of Vision, and bioRxiv (Cold Spring Harbor Laboratory).

Significant recent papers authored or coauthored by Matthias Bethge include:

  • Shortcut learning in deep neural networks, 2020, Nature Machine Intelligence
  • Improving robustness against common corruptions by covariate shift adaptation, 2020, arXiv (Cornell University)
  • Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX, 2020, The Journal of Open Source Software
  • DeepGaze III: Modeling free-viewing human scanpaths with deep learning, 2022, Journal of Vision
  • DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Best Publications

  • Image Style Transfer Using Convolutional Neural Networks

    Leon A. Gatys;Alexander S. Ecker;Matthias Bethge

  • DeepLabCut: markerless pose estimation of user-defined body parts with deep learning

    Alexander Mathis;Pranav Mamidanna;Kevin M. Cury;Taiga Abe

  • A Neural Algorithm of Artistic Style

    Leon A. Gatys;Alexander S. Ecker;Matthias Bethge

  • Shortcut learning in deep neural networks

    Robert Geirhos;Jörn-Henrik Jacobsen;Claudio Michaelis;Richard S. Zemel

  • Using DeepLabCut for 3D markerless pose estimation across species and behaviors

    Tanmay Nath;Alexander Mathis;An Chi Chen;Amir Patel

  • ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

    Robert Geirhos;Patricia Rubisch;Claudio Michaelis;Matthias Bethge

  • Texture synthesis using convolutional neural networks

    Leon A. Gatys;Alexander S. Ecker;Matthias Bethge

  • Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

    Wieland Brendel;Jonas Rauber;Matthias Bethge

  • A note on the evaluation of generative models

    Lucas Theis;Aäron van den Oord;Matthias Bethge

  • Electrophysiological, transcriptomic and morphologic profiling of single neurons using Patch-seq

    Cathryn R Cadwell;Athanasia Palasantza;Athanasia Palasantza;Xiaolong Jiang;Philipp Berens

  • Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models

    Jonas Rauber;Wieland Brendel;Matthias Bethge

  • Controlling Perceptual Factors in Neural Style Transfer

    Leon A. Gatys;Alexander S. Ecker;Matthias Bethge;Aaron Hertzmann

  • Generalisation in humans and deep neural networks

    Robert Geirhos;Carlos R. Medina Temme;Jonas Rauber;Heiko H. Schütt

  • State dependence of noise correlations in macaque primary visual cortex

    Alexander S. Ecker;Philipp Berens;Philipp Berens;R. James Cotton;Manivannan Subramaniyan

  • Deep convolutional models improve predictions of macaque V1 responses to natural images.

    Santiago A. Cadena;Santiago A. Cadena;George H. Denfield;Edgar Y. Walker;Leon A. Gatys

  • Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

    Matthias Kümmerer;Lucas Theis;Matthias Bethge

  • The Effect of Noise Correlations in Populations of Diversely Tuned Neurons

    Alexander S. Ecker;Philipp Berens;Andreas S. Tolias;Matthias Bethge

  • DeepGaze II: Reading fixations from deep features trained on object recognition.

    Matthias Kümmerer;Thomas S. A. Wallis;Matthias Bethge

  • Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

    Wieland Brendel;Matthias Bethge

  • Inhibition decorrelates visual feature representations in the inner retina

    Katrin Franke;Philipp Berens;Timm Schubert;Matthias Bethge

  • Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

    Claudio Michaelis;Benjamin Mitzkus;Robert Geirhos;Evgenia Rusak

  • Improving robustness against common corruptions by covariate shift adaptation

    Steffen Schneider;Evgenia Rusak;Luisa Eck;Oliver Bringmann

  • Markerless tracking of user-defined features with deep learning

    Alexander Mathis;Pranav Mamidanna;Taiga Abe;Kevin M. Cury

Frequent Co-Authors

Andreas S. Tolias
Andreas S. Tolias Baylor College of Medicine
Jakob H. Macke
Jakob H. Macke Max Planck Institute for Intelligent Systems
Felix A. Wichmann
Felix A. Wichmann University of Tübingen
Thomas Euler
Thomas Euler University of Tübingen
Alexander Mathis
Alexander Mathis École Polytechnique Fédérale de Lausanne
Matthias Seeger
Matthias Seeger Amazon (Germany)
Manfred Opper
Manfred Opper Technical University of Berlin
Rachel Mandelbaum
Rachel Mandelbaum Carnegie Mellon University
Konrad Kuijken
Konrad Kuijken Leiden University
Catherine Heymans
Catherine Heymans University of Edinburgh

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to numerous online degrees and career opportunities. Many students are now seeking easy online degrees that pay well, which can deliver strong salaries while offering flexible study schedules. This approach works well for those balancing work or family commitments.

Technology-focused degrees are especially popular. If you're passionate about innovation, consider an ai online degree. Artificial intelligence is a fast-growing field with employers actively seeking talent.

Deciding on your major matters. The best degree for you depends on your interests and career goals, but Computer Science consistently ranks at the top due to its versatility and earning potential.

For those looking to advance quickly, an easy masters degree could help boost credentials without years of study. By exploring these options, you can find affordable, flexible, and high-reward pathways aligned with your ambitions.

Best Scientists Citing Matthias Bethge

Trending Scientists

Recently Published Articles