Image Classification on ImageNet-1K (val) (Zero-Shot Top-1 Accuracy)
76.6Top-1 Acc (Zero-Shot)CLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIPvisual encoder=ViT-L/14-336, visual FLOPS=191.0G2023.12 | 76.6 | |
| SF-LCLIPvisual encoder=SF-LCLIP, tokens=144, visual FLOPS=33.9G2023.12 | 75.9 | |
| CLIPvisual encoder=ViT-L/14-224, visual FLOPS=81.1G2023.12 | 75.4 | |
| SF-LCLIPvisual encoder=SF-LCLIP, tokens=128, visual FLOPS=30.0G2023.12 | 74.9 | |
| SF-LCLIPvisual encoder=SF-LCLIP, tokens=64, visual FLOPS=14.8G2023.12 | 73.6 | |
| CLIPvisual encoder=ViT-B/16-224, visual FLOPS=17.5G2023.12 | 68.3 | |
| SF-BCLIPvisual encoder=SF-BCLIP, tokens=49, visual FLOPS=3.8G2023.12 | 66 | |
| TinyCLIPvisual encoder=ViT-63M/32-224, visual FLOPS=2.0G2023.12 | 64.5 | |
| CLIPvisual encoder=ViT-B/32-224, visual FLOPS=4.4G2023.12 | 63.3 |