HyperAI
HyperAI超神経
ホーム
プラットフォーム
ドキュメント
ニュース
論文
チュートリアル
データセット
百科事典
SOTA
LLMモデル
GPU ランキング
学会
検索
サイトについて
日本語
HyperAI
HyperAI超神経
Toggle sidebar
サイトを検索…
⌘
K
Command Palette
Search for a command to run...
ホーム
SOTA
画像生成
Image Generation On Cifar 10
Image Generation On Cifar 10
評価指標
FID
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
Columns
モデル名
FID
Paper Title
Repository
PresGAN
52.202
Prescribed Generative Adversarial Networks
RESFLOW
48.29
-
-
Residual Flow
46.37
Residual Flows for Invertible Generative Modeling
GLF+perceptual loss (ours)
44.6
Generative Latent Flow
ProdPoly no activation functions
40.45
Deep Polynomial Neural Networks
ACGAN
35.47
-
-
DenseFlow-74-10
34.90
Densely connected normalizing flows
NVAE w/ flow
32.53
NVAE: A Deep Hierarchical Variational Autoencoder
QSNGAN
31.966
Quaternion Generative Adversarial Networks
WGAN-GP
29.3
Improved Training of Wasserstein GANs
MSGAN
28.73
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
FOGAN
27.4
First Order Generative Adversarial Networks
HingeGAN
27.12
Gradient penalty from a maximum margin perspective
RSGAN-GP
25.60
The relativistic discriminator: a key element missing from standard GAN
NCSN
25.32
Generative Modeling by Estimating Gradients of the Data Distribution
SN-SMMDGAN
25.0
On gradient regularizers for MMD GANs
WGAN-GP + TT Update Rule
24.8
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
NCP-VAE
24.08
A Contrastive Learning Approach for Training Variational Autoencoder Priors
-
CLR-GAN
23.3
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction
-
SN-GANs
21.7
Spectral Normalization for Generative Adversarial Networks
0 of 70 row(s) selected.
Previous
Next