Zero Shot Object Detection On Lvis V1 0 Val
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 |
|---|---|---|---|
| CP-DETR-Pro(without LVIS data) | 51.6 | CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection | - |
| MQ-GLIP-L | 34.7 | Multi-modal Queried Object Detection in the Wild | |
| GLIP-L | 26.9 | Grounded Language-Image Pre-training | |
| Grounding DINO 1.6 Pro (without LVIS data) | 51.1 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| OWLv2 (OWL-ST+FT) | 47.0 | Scaling Open-Vocabulary Object Detection | |
| MQ-GroundingDINO-T | 22.1 | Multi-modal Queried Object Detection in the Wild | |
| MQ-GLIP-T | 22.6 | Multi-modal Queried Object Detection in the Wild | |
| Grounding DINO 1.5 Pro (without LVIS data) | 47.7 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| OV-DINO-T (without LVIS data, swin tiny) | 32.9 | OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion |
0 of 9 row(s) selected.