📊 Showing 5 results | 📏 Metric: Top 1 Accuracy
| Rank | Model | Paper | Top 1 Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | MAWS (ViT-2B) | The effectiveness of MAE pre-pretraining for billion-scale pretraining | 96.20 | 2023-03-23 | 📦 facebookresearch/maws |
| 2 | EVA-CLIP-18B | EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters | 95.80 | 2024-02-06 | 📦 baaivision/EVA 📦 baaivision/eva |
| 3 | InternVL-C | InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks | 95.30 | 2023-12-21 | 📦 opengvlab/internvl 📦 opengvlab/internvl-mmdetseg |
| 4 | EVA-CLIP-E/14+ | EVA-CLIP: Improved Training Techniques for CLIP at Scale | 94.90 | 2023-03-27 | 📦 baaivision/eva 📦 PaddlePaddle/PaddleMIX 📦 Yui010206/CREMA 📦 jaehong31/raccoon |
| 5 | Diffusion Classifier (zero-shot) | Your Diffusion Model is Secretly a Zero-Shot Classifier | 77.70 | 2023-03-28 | 📦 diffusion-classifier/diffusion-classifier 📦 SamsungSAILMontreal/ForestDiffusion 📦 tajamul21/fate 📦 LiYinqi/DIVE |