| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification | ✓ Link | 96.37 | CODER* (CLIP ViT-L/14@336px) | 2024-04-27 |
| Demystifying CLIP Data | ✓ Link | 95.7 | MetaCLIP ViT-bigG/14 | 2023-09-28 |
| Multi-label Cluster Discrimination for Visual Representation Learning | ✓ Link | 93.9 | MLCD ViT-L/14 | 2024-07-24 |
| FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models | 86.5 | FFF-ViT-B/32 (Open70M) (extra data) | 2024-05-16 | |
| FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication | 83.09 | FairDeDup (50%) | 2024-04-24 |