Robert Geirhos

rgeirhos's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 7 papers about 9 hours ago

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

Paper • 1811.12231 • Published Nov 29, 2018 • 1

Scaling Vision Transformers to 22 Billion Parameters

Paper • 2302.05442 • Published Feb 10, 2023 • 2

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Paper • 2307.06304 • Published Jul 12, 2023 • 29

Intriguing properties of generative classifiers

Paper • 2309.16779 • Published Sep 28, 2023 • 1

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

Paper • 2403.09193 • Published Mar 14, 2024 • 1

Towards flexible perception with visual memory

Paper • 2408.08172 • Published Aug 15, 2024 • 23

Do generative video models learn physical principles from watching videos?

Paper • 2501.09038 • Published 3 days ago • 8