Object Detection On Odinw Full Shot 13 Tasks
평가 지표
AP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | AP | Paper Title | Repository |
|---|---|---|---|
| CP-DETR-L(only optimize prompt) | 73.1 | CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection | - |
| MQ-GLIP-L | 71.3 | Multi-modal Queried Object Detection in the Wild | |
| Grounding DINO 1.5 Pro | 72.4 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| Grounding DINO | 70.9 | Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection | |
| DetCLIPv2 | 70.4 | DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment | - |
| GLIPv2 | 70.4 | GLIPv2: Unifying Localization and Vision-Language Understanding | |
| DetCLIPv3 | 72.1 | DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection | - |
| GLIP | 68.9 | Grounded Language-Image Pre-training |
0 of 8 row(s) selected.