Described Object Detection On Description
評価指標
Intra-scenario ABS mAP
Intra-scenario FULL mAP
Intra-scenario PRES mAP
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 | Intra-scenario ABS mAP | Intra-scenario FULL mAP | Intra-scenario PRES mAP | Paper Title | Repository |
|---|---|---|---|---|---|
| SPHINX-7B | 7.9 | 10.6 | 11.4 | SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models | - |
| CORA-R50 | 5.0 | 6.2 | 6.7 | CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching | - |
| OFA-DOD-base | 15.4 | 21.6 | 23.7 | Described Object Detection: Liberating Object Detection with Flexible Expressions | - |
| GLIP-T | 21.5 | 19.1 | 18.3 | Grounded Language-Image Pre-training | - |
| UNINEXT-large | 15.9 | 17.9 | 18.6 | Universal Instance Perception as Object Discovery and Retrieval | - |
| FIBER-B | 26.0 | 22.7 | 21.5 | Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone | - |
| MM-Grounding-DINO | 26.0 | 22.9 | 21.9 | An Open and Comprehensive Pipeline for Unified Object Grounding and Detection | - |
| OWL-ViT-base | 8.8 | 8.6 | 8.5 | Simple Open-Vocabulary Object Detection with Vision Transformers | - |
0 of 8 row(s) selected.