Text-based Image Retrieval on Fashion200k
20.1Rank-1 AccTIRG* + EATV+L
Evaluation results
| Method | Links | |
|---|---|---|
| TIRG* + EATV+Lreproduction=true, vision_backbone=EAT-V, language_backbone=EAT-L2021.05 | 20.1 | |
| TIRG* + EATVreproduction=true, vision_backbone=EAT-V2021.05 | 19.9 | |
| TIRG* + R101vreproduction=true, vision_backbone=ResNet-1012021.05 | 19 | |
| TIRG* + EATLreproduction=true, language_backbone=EAT-L2021.05 | 14.9 | |
| TIRG* + TRreproduction=true, language_backbone=Naive Transformer2021.05 | 14.3 | |
| TIRG2021.05 | 14.1 | |
| TIRG*reproduction=true2021.05 | 14 |