Referring Expression Comprehension on RefCOCO+ v1 (testA)
87.4Top-1 AccuracyGrounding-DINO-T
Evaluation results
| Method | Links | |
|---|---|---|
| Grounding-DINO-TPre-training Data=O365, GoldG, RefC, Fine-tuning=true2024.04 | 87.4 | |
| DQ-DETRPre-training Data=GoldG, RefC, Fine-tuning=true2024.04 | 86.15 | |
| HyperLearnerPre-training Data=O365, GoldG, RefC, Fine-tuning=true2024.04 | 84.7 | |
| MDETRPre-training Data=GoldG, RefC, Fine-tuning=true2024.04 | 84.09 | |
| RefTRPre-training Data=VG, Fine-tuning=true2024.04 | 82.26 | |
| HyperLearnerPre-training Data=O365, GoldG, RefC, Fine-tuning=false2024.04 | 75.55 | |
| MAttNetPre-training Data=RefC, Fine-tuning=true2024.04 | 71.62 | |
| Grounding-DINO-TPre-training Data=O365, GoldG, RefC, Fine-tuning=false2024.04 | 69.91 | |
| HyperLearnerPre-training Data=O365, GoldG, Fine-tuning=false2024.04 | 62.29 | |
| Grounding-DINO-TPre-training Data=O365, GoldG, Fine-tuning=false2024.04 | 57.59 | |
| GLIP-T(B)Pre-training Data=O365, GoldG, Fine-tuning=false2024.04 | 53.44 | |
| GLIP-T(C)Pre-training Data=O365, GoldG, Cap4M, Fine-tuning=false2024.04 | 52.78 | |
| CNN-LSTMPre-training Data=RefC, Fine-tuning=true2024.04 | 42.13 |