LiT-22B

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision5 results

Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2023-02-10
80.9
best: 81.2 (BASIC (Lion))
SOTA
Scaling Vision Transformers to 22 Billion Parameters arXiv:2302.05442
Zero-Shot Transfer Image ClassificationonObjectNet
Accuracy (Private)· 2023-02-10
87.6
SOTA
Scaling Vision Transformers to 22 Billion Parameters arXiv:2302.05442
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2023-02-10
90.1
best: 90.2 (CoCa)
Scaling Vision Transformers to 22 Billion Parameters arXiv:2302.05442
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2023-02-10
85.9
best: 88.5 (M2-Encoder)
Scaling Vision Transformers to 22 Billion Parameters arXiv:2302.05442
Zero-Shot Transfer Image ClassificationonImageNet-R
Accuracy· 2023-02-10
96
best: 96.8 (BASIC (Lion))
Scaling Vision Transformers to 22 Billion Parameters arXiv:2302.05442