Image Classification on ImageNet 1k (val) (Standard, Last, and Oracle Accuracy)
90.52AccuracyLion
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LionModel=ViT-g/14, Input Resolution=518x518, #Params=1.04B, Pre-training Dataset=JFT-3B2023.02 | 90.52 | — | — | |
| AdafactorModel=ViT-G/14, Input Resolution=518x518, #Params=1.88B, Pre-training Dataset=JFT-3B2023.02 | 90.45 | — | — | |
| AdafactorModel=ViT-g/14, Input Resolution=518x518, #Params=1.04B, Pre-training Dataset=JFT-3B2023.02 | 90.25 | — | — | |
| LionModel=ViT-H/14, Input Resolution=518x518, #Params=633.47M, Pre-training Dataset=JFT-300M2023.02 | 89.09 | — | — | |
| AdamWModel=ViT-H/14, Input Resolution=518x518, #Params=633.47M, Pre-training Dataset=JFT-300M2023.02 | 88.55 | — | — | |
| LionModel=ViT-L/16, Input Resolution=512x512, #Params=305.18M, Pre-training Dataset=JFT-300M2023.02 | 88.5 | — | — | |
| AdamWModel=ViT-L/16, Input Resolution=512x512, #Params=305.18M, Pre-training Dataset=JFT-300M2023.02 | 87.72 | — | — | |
| LionModel=ViT-G/14, Input Resolution=518x518, #Params=1.88B, Pre-training Dataset=JFT-3B2023.02 | — | 90.71 | 90.71 |