arxiv:2501.09038
Robert Geirhos
rgeirhos
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 14 hours ago
ImageNet-trained CNNs are biased towards texture; increasing shape bias
improves accuracy and robustness
upvoted
a
paper
about 14 hours ago
Scaling Vision Transformers to 22 Billion Parameters
upvoted
a
paper
about 14 hours ago
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and
Resolution
Organizations
None yet
models
None public yet
datasets
None public yet