Referring Expression Comprehension on RefCOCO (Accuracy)
89.5AccuracyQwen2.5-VL-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-7BToken Budget=Full2026.01 | 89.5 | |
| VisionTrimToken Budget=~1/32026.01 | 86.8 | |
| SparseVLMToken Budget=~1/32026.01 | 78.4 | |
| PaliGemma2-10BResolution=448x448, Fine-tuning=per-task2025.12 | 78.2 | |
| PaliGemma2-3B + AuditDMResolution=448x448, Fine-tuning=per-task2025.12 | 77.8 | |
| PDropToken Budget=~1/32026.01 | 77.5 | |
| PaliGemma2-28BResolution=448x448, Fine-tuning=per-task2025.12 | 77.3 | |
| PaliGemma2-3BResolution=448x448, Fine-tuning=per-task2025.12 | 76.3 | |
| FastVToken Budget=~1/32026.01 | 73.6 |