Image Classification on YouTube-BB
95.3PM0CLIP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CLIPModel=ViT-L/14@336, Pre-training Data=WIT-400M, Evaluation Protocol=our eval., Image size=3362022.12 | 95.3 | 89.4 | |
| CLIPEvaluation Protocol=Zero-Shot2021.02 | 95.2 | 88.5 | |
| CLIPModel=ViT-L/14@336, Pre-training Data=WIT-400M, Image size=3362022.12 | 95.2 | 88.5 | |
| CLIPModel=ViT-L/14, Pre-training Data=WIT-400M, Evaluation Protocol=our eval., Image size=2242022.12 | 94.1 | 86.4 | |
| FLIPModel=ViT-L/14, Pre-training Data=LAION-400M, Image size=2242022.12 | 89.4 | 83.3 | |
| OpenCLIPModel=ViT-L/14, Pre-training Data=LAION-400M, Evaluation Protocol=our eval., Image size=2242022.12 | 86.5 | 77.8 | |
| CLIPModel=ViT-L/14, Pre-training Data=LAION-400M, Evaluation Protocol=our repro., Image size=2242022.12 | 85.7 | 77.8 | |
| FixResNeXt101-32x48d V22021.02 | 68.9 | 57.7 | |
| CLIPEvaluation Protocol=Linear Probe2021.02 | 68.7 | 63.1 | |
| NS EfficientNet-L22021.02 | 67.7 | 63.5 |