Robert Geirhos

Orcid: 0000-0001-7698-3187

According to our database1, Robert Geirhos authored at least 27 papers between 2015 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
CoRR, 2024

2023
Neither hype nor gloom do DNNs justice.
CoRR, 2023

Getting aligned on representational alignment.
CoRR, 2023

Intriguing properties of generative classifiers.
CoRR, 2023

Don't trust your eyes: on the (un)reliability of feature visualizations.
CoRR, 2023

Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?
CoRR, 2023

Scaling Vision Transformers to 22 Billion Parameters.
CoRR, 2023

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023


2022
Irren ist menschlich: Aber was, wenn Maschinen Fehler machen?
Ausgezeichnete Informatikdissertationen, 2022

To err is human? A functional comparison of human and machine decision-making.
PhD thesis, 2022

The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks.
CoRR, 2022

Beyond neural scaling laws: beating power law scaling via data pruning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond).
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Partial success in closing the gap between human and machine vision.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization.
Proceedings of the 9th International Conference on Learning Representations, 2021

2020
Shortcut learning in deep neural networks.
Nat. Mach. Intell., 2020

Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations.
CoRR, 2020

On the surprising similarities between supervised and self-supervised models.
CoRR, 2020

Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming.
CoRR, 2019

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
Generalisation in humans and deep neural networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017
Comparing deep neural networks against humans: object recognition when the signal gets weaker.
CoRR, 2017

Methods and measurements to compare men against machines.
Proceedings of the Human Vision and Electronic Imaging 2017, Burlingame, CA, USA, 29 January 2017, 2017

2015
An Automatized Heider-Simmel Story Generation Tool.
Proceedings of the 37th Annual Meeting of the Cognitive Science Society, 2015


  Loading...