Image Generation On Stl 10

评估指标

FID

Inception score

评测结果

各个模型在此基准测试上的表现结果

			Paper Title	Repository
QSNGAN	59.611	4.987	Quaternion Generative Adversarial Networks
PeerGAN	51.37	-	DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training	-
ProbGAN	46.74	8.87	ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees	-
DC-VAE	41.9	8.1	Dual Contradistinctive Generative Autoencoder	-
SN-GAN	40.1	9.10	Spectral Normalization for Generative Adversarial Networks
Improving MMD GAN	37.63	9.34	Improving MMD-GAN Training with Repulsive Loss Function
Dist-GAN	36.19	-	Dist-GAN: An Improved GAN using Distance Constraints
aw-SN-GAN	34.72	9.61	Adaptive Weighted Discriminator for Training Generative Adversarial Networks
AutoGAN	31.01	9.16	AutoGAN: Neural Architecture Search for Generative Adversarial Networks
DEGAS	28.76	9.71	DEGAS: Differentiable Efficient Generator Search	-
aw-AutoGAN	26.32	9.59	Adaptive Weighted Discriminator for Training Generative Adversarial Networks
E2GAN	25.35	9.51	Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search
EAGAN (G)	23.34	10.02	EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
SNGAN-DCD (Pixel)	22.25	9.25	Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
EAGAN (G+D)	22.18	10.44	EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
PGMGAN	19.52	11.16	Partition-Guided GANs
TransGAN	18.28	10.43	TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
SNGAN-DCD (Latent)	17.68	9.33	Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
Styleformer	15.17	11.01	Styleformer: Transformer based Generative Adversarial Networks with Style Vector
MMD-AdversarialNAS (Compressed Small)	14.84	11.66	Enhancing GAN Performance through Neural Architecture Search and Tensor Decomposition	-

0 of 31 row(s) selected.