Region-Set Captioning on COCO Entities
109.1C ScorePatch-ioner
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Patch-ionerConfiguration=T2D + Mem., Number of Parameters=0.21B, Adaptation strategy=Patch-based2025.10 | 109.1 | 87.5 | |
| Llava1.5 One-VisionAdaptation strategy=Crop, Number of Parameters=4B2025.10 | 75.9 | 86.7 | |
| Llava1.5 One-VisionAdaptation strategy=Visual Prompting, Number of Parameters=4B2025.10 | 72.2 | 87.3 | |
| Qwen2.5 VLAdaptation strategy=Crop, Number of Parameters=3B2025.10 | 68.6 | 85.9 | |
| Qwen2.5 VLAdaptation strategy=Visual Prompting, Number of Parameters=3B2025.10 | 59.6 | 84.5 | |
| Qwen3 VLAdaptation strategy=Crop, Number of Parameters=4B2025.10 | 20.2 | 80.4 | |
| Qwen3 VLAdaptation strategy=Visual Prompting, Number of Parameters=4B2025.10 | 10.8 | 74.2 |