Conditional Image Generation On Imagenet 2
Metriken
FID
Inception score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | FID | Inception score |
|---|---|---|
| instance-conditioned-gan | 8.2±0.1 | 173.8±0.9 |
| stabilize-the-latent-space-for-image | 3.39 | 205.96 |
| diffusion-models-beat-gans-on-image-synthesis | 4.59 | 186.7 |
| instance-conditioned-gan | 8.1 | 144.2 |
| entropy-driven-sampling-and-training-scheme | 4.09 | 221.57 |