Conditional Image Generation On Imagenet

Métriques

FID

Inception score

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	FID	Inception score	Paper Title	Repository
Omni-GAN	8.30	190.94	Omni-GAN: On the Secrets of cGANs and Beyond	-
simple diffusion (U-ViT, L)	3.23	171.9	Simple diffusion: End-to-end diffusion for high resolution images	-
Projection Discriminator	27.62	36.8	cGANs with Projection Discriminator	-
FQ-GAN	13.77	54.36	Feature Quantization Improves GAN Training	-
ADM-G + EDS (ED-DPM, classifier_scale=0.4)	2.63	159.72	Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation	-
BigGAN-deep	5.7	124.5	Large Scale GAN Training for High Fidelity Natural Image Synthesis	-
BigGAN	8.7	98.8	Large Scale GAN Training for High Fidelity Natural Image Synthesis	-
AC-GAN	-	28.5	Conditional Image Synthesis With Auxiliary Classifier GANs	-
S3 GAN	7.7	83.1	High-Fidelity Image Generation With Fewer Labels	-
BigGAN + instance selection	9.61	114.32	Instance Selection for GANs	-
ADM-G + EDS + ECT (ED-DPM, classifier_scale=0.6)	2.68	169.24	Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation	-
SAGAN	18.65	52.52	Self-Attention Generative Adversarial Networks	-
Your Local GAN	15.94	57.22	Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models	-
EluCD_DDPM	2.19	-	Elucidating The Design Space of Classifier-Guided Diffusion Generation	-
Omni-INR-GAN	6.53	262.85	Omni-GAN: On the Secrets of cGANs and Beyond	-
CR-BigGAN	6.66	-	Consistency Regularization for Generative Adversarial Networks	-
IC-GAN + DA	9.5	108.6	Instance-Conditioned GAN	-
ADC-GAN	8.02	108.10	Conditional GANs with Auxiliary Discriminative Classifier	-
HamGAN	14.80	58.75	Is Attention Better Than Matrix Decomposition?	-
ADM-G (classifier_scale=0.5)	2.97	-	Diffusion Models Beat GANs on Image Synthesis	-

0 of 22 row(s) selected.