Reproducible scaling laws for contrastive language-image learning
Paper
•
2212.07143
•
Published
•
2
Ross Wightman
rwightman
AI & ML interests
Computer vision, transfer learning, semi/self supervised learning, robotics.
Recent Activity
new activity
4 days ago
timm/vit_small_patch16_dinov3_qkvb.lvd1689m:Regarding the Feature extractor
updated
a model
4 days ago
timm/csatv2.r512_in1k
updated
a model
4 days ago
timm/csatv2_21m.sw_r640_in1k
Organizations
authored
4
papers
almost 3 years ago
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Paper
•
2106.10270
•
Published
•
3
LAION-5B: An open large-scale dataset for training next generation image-text models
Paper
•
2210.08402
•
Published
•
5
ResNet strikes back: An improved training procedure in timm
Paper
•
2110.00476
•
Published
•
6