Text-to-Image Retrieval on MS-COCO 5K full set (test)
78.5R@1SEPS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SEPSVisual Encoder=ViT-Base-384, Textual Encoder=BERT-base, Image Resolution=384x384, Patch Size=24x24, Fine-Grained Alignment (FG)=true2025.11 | 78.5 | 96.3 | 98.7 | 534.6 | |
| SEPSVisual Encoder=ViT-Base-224, Textual Encoder=BERT-base, Image Resolution=224x224, Patch Size=14x14, Fine-Grained Alignment (FG)=true2025.11 | 73.5 | 94.5 | 97.8 | 516.9 | |
| SEPSVisual Encoder=Swin-Base-384, Textual Encoder=BERT-base, Image Resolution=384x384, Patch Size=12x12, Fine-Grained Alignment (FG)=true2025.11 | 70.3 | 93.8 | 97.6 | 519.1 | |
| SEPSVisual Encoder=Swin-Base-224, Textual Encoder=BERT-base, Image Resolution=224x224, Patch Size=7x7, Fine-Grained Alignment (FG)=true2025.11 | 66.8 | 92.2 | 96.8 | 506.1 |