Robert Geirhos's picture

7

Robert Geirhos

rgeirhos

https://robertgeirhos.com/

AI & ML interests

None yet

Recent Activity

upvoted a paper 25 days ago

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

upvoted a paper 25 days ago

Scaling Vision Transformers to 22 Billion Parameters

upvoted a paper 25 days ago

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

View all activity

Organizations

None yet

Papers 7

arxiv:2501.09038

arxiv:2408.08172

arxiv:2403.09193

arxiv:2309.16779

models

None public yet

datasets

None public yet