Zero Shot Object Detection On Lvis V1 0
評価指標
AP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | AP | Paper Title | Repository |
|---|---|---|---|
| Grounding DINO 1.6 Pro (without LVIS data) | 57.7 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| Grounding DINO 1.5 Pro (without LVIS data) | 55.7 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| MQ-GLIP-L | 43.4 | Multi-modal Queried Object Detection in the Wild | |
| MQ-GLIP-T | 30.4 | Multi-modal Queried Object Detection in the Wild | |
| GroundingDINO-L | 33.9 | Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection | |
| MQ-GroundingDINO-T | 30.2 | Multi-modal Queried Object Detection in the Wild | |
| GLIP-L | 37.3 | Grounded Language-Image Pre-training | |
| OV-DINO-T (without LVIS data, swin tiny) | 40.1 | OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion | |
| CP-DETR-Pro(without LVIS data) | 58.2 | CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection | - |
| YOLO-World-L | 35.4 | YOLO-World: Real-Time Open-Vocabulary Object Detection | |
| OWLv2 (OWL-ST+FT) | 51.3 | Scaling Open-Vocabulary Object Detection |
0 of 11 row(s) selected.