Image Classification (Linear Probe) on ImageNet V2 1.0
75.1Top-1 AccuracyCLIP-VIT-L/14
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CLIP-VIT-L/14Backbone=ViT-L/14, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=321, # Inference Params (M)=3212024.11 | 75.1 | — | |
| TinyVit-21MBackbone=TinyVit-21M, Over-parameterization method=OPDF, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=38, # Inference Params (M)=212024.11 | 74.9 | 93.4 | |
| TinyVit-21MBackbone=TinyVit-21M, Over-parameterization method=None, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=21, # Inference Params (M)=212024.11 | 73 | 91.9 | |
| TinyVit-11MBackbone=TinyVit-11M, Over-parameterization method=OPDF, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=23, # Inference Params (M)=112024.11 | 72.4 | 92.6 | |
| TinyVit-21MBackbone=TinyVit-21M, Over-parameterization method=SVD, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=29, # Inference Params (M)=212024.11 | 71.8 | 92.4 | |
| TinyVit-11MBackbone=TinyVit-11M, Over-parameterization method=SVD, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=17, # Inference Params (M)=112024.11 | 71.7 | 91.4 | |
| TinyVit-11MBackbone=TinyVit-11M, Over-parameterization method=None, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=11, # Inference Params (M)=112024.11 | 70.7 | 90.4 | |
| TinyVit-5MBackbone=TinyVit-5M, Over-parameterization method=OPDF, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=9.9, # Inference Params (M)=5.42024.11 | 69.4 | 88.9 | |
| TinyVit-5MBackbone=TinyVit-5M, Over-parameterization method=SVD, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=7.6, # Inference Params (M)=5.42024.11 | 68.7 | 88.4 | |
| TinyVit-5MBackbone=TinyVit-5M, Over-parameterization method=None, Pre-trained=ImageNet-21k, Evaluation Protocol=linear probe, # Train Params (M)=5.4, # Inference Params (M)=5.42024.11 | 66.8 | 87.6 |