Metric: AP (higher is better)
| # | Model↕ | AP▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | CP-DETR-L(only optimize prompt) | 73.1 | No | CP-DETR: Concept Prompt Guide DETR Toward Strong... | 2024-12-13 | - |
| 2 | Grounding DINO 1.5 Pro | 72.4 | No | Grounding DINO 1.5: Advance the "Edge" of Open-S... | 2024-05-16 | Code |
| 3 | DetCLIPv3 | 72.1 | No | DetCLIPv3: Towards Versatile Generative Open-voc... | 2024-04-14 | - |
| 4 | MQ-GLIP-L | 71.3 | No | Multi-modal Queried Object Detection in the Wild | 2023-05-30 | Code |
| 5 | Grounding DINO | 70.9 | No | Grounding DINO: Marrying DINO with Grounded Pre-... | 2023-03-09 | Code |
| 6 | DetCLIPv2 | 70.4 | No | DetCLIPv2: Scalable Open-Vocabulary Object Detec... | 2023-04-10 | - |
| 7 | GLIPv2 | 70.4 | No | GLIPv2: Unifying Localization and Vision-Languag... | 2022-06-12 | Code |
| 8 | GLIP | 68.9 | No | Grounded Language-Image Pre-training | 2021-12-07 | Code |