| Paper | Code | mIoU | ModelName | ReleaseDate |
|---|---|---|---|---|
| UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding | ✓ Link | 85.4 | UMG-CLIP-E/14 | 2024-01-12 |
| CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation | ✓ Link | 82.5 | CAT-Seg | 2023-03-21 |
| SILC: Improving Vision Language Pretraining with Self-Distillation | 82.5 | SILC | 2023-10-20 | |
| Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP | ✓ Link | 81.8 | FC-CLIP | 2023-08-04 |