( en | de | ru )

 

Disambiguation of "Geirhos, Robert"

Author of the publication

copydeleteadd this publication to your clipboard
Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond).

, , , and . ICLR, OpenReview.net, (2022)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Bettina Geirhos

Robert Klöfkorn

Numerics for evolution equations: a general interface based design concept. Uni Freiburg, (2009)

Robert Wille

Towards a design flow for reversible logic. Uni Bremen, (2009)

Robert Braun

Referenzmodellierung: Grundlegung und Evaluation der Technik des Modell-Konfigurationsmanagements. TU Dresden, (2010)

Robert Wagner

Inkrementelle Modellsynchronisation. Uni Paderborn, (2009)
 

Other publications of authors with the same name

Methods and measurements to compare men against machines., , , , , , and . HVEI, page 36-45. Society for Imaging Science and Technology, (2017)Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization., , , , , , and . ICLR, OpenReview.net, (2021)Scaling Vision Transformers to 22 Billion Parameters., , , , , , , , , and 32 other author(s). ICML, volume 202 of Proceedings of Machine Learning Research, page 7480-7512. PMLR, (2023)Getting aligned on representational alignment., , , , , , , , , and 19 other author(s). CoRR, (2023)Are Vision Language Models Texture or Shape Biased and Can We Steer Them?, , , , , , , and . CoRR, (2024)To err is human? A functional comparison of human and machine decision-making.. University of Tübingen, Germany, (2022)Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)., , , and . ICLR, OpenReview.net, (2022)ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness., , , , , and . ICLR, OpenReview.net, (2019)ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness., , , , , and . CoRR, (2018)Beyond neural scaling laws: beating power law scaling via data pruning., , , , and . NeurIPS, (2022)