2.1k citations · 3.9k across the 22 of their papers we have counts for
22 papers
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
Fanfei Li, Thomas Klein, Wieland Brendel +2
Out-of-distribution (OOD) robustness is a desired property of computer vision models. Improving model robustness requires high-quality signals from robustness benchmarks to quantif…
Do generative video models understand physical principles?
Saman Motamed, Laura Culp, Kevin Swersky +2
AI video generation is undergoing a revolution, with quality and realism advancing rapidly. These advances have led to a passionate scientific debate: Do video models learn "world…
We Can't Understand AI Using our Existing Vocabulary
John Hewitt, Robert Geirhos, Been Kim
This position paper argues that, in order to understand AI, we cannot rely on our existing vocabulary of human words. Instead, we should strive to develop neologisms: new words tha…
Learning Visual Composition through Improved Semantic Guidance
Austin Stone, Hagen Soltau, Robert Geirhos +6
Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual represent…
Towards flexible perception with visual memory
Robert Geirhos, Priyank Jaini, Austin Stone +5
Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is hard, since all infor…
Can We Talk Models Into Seeing the World Differently?
Paul Gavrikov, Jovita Lukasik, Steffen Jung +4
Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…
Intriguing properties of generative classifiers
Priyank Jaini, Kevin Clark, Robert Geirhos
What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more…
Don't trust your eyes: on the (un)reliability of feature visualizations
Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau +2
How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization…
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Visio…
Beyond neural scaling laws: beating power law scaling via data pruning
Ben Sorscher, Robert Geirhos, Shashank Shekhar +2
Widely observed neural scaling laws, in which error falls off as a power of the training set size, model size, or both, have driven substantial performance improvements in deep lea…
The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks
Lukas S. Huber, Robert Geirhos, Felix A. Wichmann
In laboratory object recognition tasks based on undistorted photographs, both adult humans and Deep Neural Networks (DNNs) perform close to ceiling. Unlike adults', whose object re…
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Roland S. Zimmermann, Judy Borowski, Robert Geirhos +3
A precise understanding of why units in an artificial network respond to certain stimuli would constitute a big step towards explainable artificial intelligence. One widely used ap…
Partial success in closing the gap between human and machine vision
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus +4
A few years ago, the first CNN surpassed human performance on ImageNet. However, it soon became clear that machines lack robustness on more challenging test cases, a major obstacle…
On the surprising similarities between supervised and self-supervised models
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus +3
How do humans learn to acquire a powerful, flexible and robust representation of objects? While much of this process remains unknown, it is clear that humans do not require million…
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization
Judy Borowski, Roland S. Zimmermann, Judith Schepers +4
Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural ne…
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
Robert Geirhos, Kristof Meding, Felix A. Wichmann
A central problem in cognitive science and behavioural neuroscience as well as in machine learning and artificial intelligence research is to ascertain whether two or more decision…
Shortcut Learning in Deep Neural Networks
Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis +4
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over…
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos +5
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide…
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos, Patricia Rubisch, Claudio Michaelis +3
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more…
Generalisation in humans and deep neural networks
Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber +3
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using thr…
Comparing deep neural networks against humans: object recognition when the signal gets weaker
Robert Geirhos, David H. J. Janssen, Heiko H. Schütt +3
Human visual object recognition is typically rapid and seemingly effortless, as well as largely independent of viewpoint and object orientation. Until very recently, animate visual…