| Paper | Code | Intra-scenario FULL mAP | Intra-scenario PRES mAP | Intra-scenario ABS mAP | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| An Open and Comprehensive Pipeline for Unified Object Grounding and Detection | ✓ Link | 22.9 | 21.9 | 26.0 | MM-Grounding-DINO | 2024-01-04 |
| Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone | ✓ Link | 22.7 | 21.5 | 26.0 | FIBER-B | 2022-06-15 |
| Described Object Detection: Liberating Object Detection with Flexible Expressions | ✓ Link | 21.6 | 23.7 | 15.4 | OFA-DOD-base | 2023-07-24 |
| Grounded Language-Image Pre-training | ✓ Link | 19.1 | 18.3 | 21.5 | GLIP-T | 2021-12-07 |
| Universal Instance Perception as Object Discovery and Retrieval | ✓ Link | 17.9 | 18.6 | 15.9 | UNINEXT-large | 2023-03-12 |
| SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models | ✓ Link | 10.6 | 11.4 | 7.9 | SPHINX-7B | 2023-11-13 |
| Simple Open-Vocabulary Object Detection with Vision Transformers | ✓ Link | 8.6 | 8.5 | 8.8 | OWL-ViT-base | 2022-05-12 |
| CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching | ✓ Link | 6.2 | 6.7 | 5.0 | CORA-R50 | 2023-03-23 |