Object Detection On Lvis V1 0 Minival
評価指標
box 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 | box AP | Paper Title | Repository |
|---|---|---|---|
| Grounding DINO 1.5 Pro | 68.1 | Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | |
| Co-DETR (single-scale) | 72.0 | DETRs with Collaborative Hybrid Assignments Training | |
| CP-DETR-L Swin-L(with chunk) | 69.2 | CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection | - |
| GLIPv2 | 59.8 | GLIPv2: Unifying Localization and Vision-Language Understanding | |
| M3I Pre-training (InternImage-H, single-scale) | 65.8 | Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information | |
| InternImage-H | 65.8 | InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions |
0 of 6 row(s) selected.