Text-based Image Retrieval on CSS
73.8Rank-1TIRG* + EATV+L
Evaluation Results
| Method | Links | |
|---|---|---|
| TIRG* + EATV+Lreproduction=true, vision_backbone=EAT-V, language_backbone=EAT-L2021.05 | 73.8 | |
| TIRG* + EATVreproduction=true, vision_backbone=EAT-V2021.05 | 73.5 | |
| TIRG* + R101vreproduction=true, vision_backbone=ResNet-1012021.05 | 73 | |
| TIRG* + EATLreproduction=true, language_backbone=EAT-L2021.05 | 71 | |
| TIRG* + TRreproduction=true, language_backbone=Naive Transformer2021.05 | 70.7 | |
| TIRG*reproduction=true2021.05 | 70.1 |