Conditional Image Generation on Flickr8k
31.15FIDSTA
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| STAInput=speech2025.12 | 31.15 | — | 43.46 | |
| Fusion-S2iGanInput=speech2025.12 | 70.8 | — | 34.95 | |
| AttnGANInput=text2025.12 | 84.08 | — | 50.4 | |
| S2IGANInput=speech2025.12 | 93.29 | — | 16.4 | |
| StackGAN-v2Input=speech2025.12 | 101.74 | — | 16.4 |