View Code? Open in Web Editor
NEW
This project forked from lynnho/gan-papers
GAN papers
gan-papers's Introduction
- GAN, DCGAN
- cGAN - Label-conditioning generation
- AcGAN - Supervised generation (auxiliary classifier with labels)
- SGAN - D outputs [CLASS-1, CLASS-2, . . . CLASS-N, FAKE]
- InfoGAN - Unsupervised lantern space disentangling
- ALI, BiGAN - match p(G(z),z) and q(x,E(x))
- GMAN - Multiple discriminator models
- AdaGAN - Multiple generative models
- MGGAN - Multiple generative models
- LAPGAN - Coarse-to-fine generation
- StackGAN - Two-step generation
- PGGAN
Function ('~' means 'match')
- GAN, DCGAN
g(Z|Y) ~ X|Y, where Y is label or lantern variable
- cGAN
- AcGAN
- InfoGAN
- CFGAN
- ALI, BiGAN
- GAN, DCGAN - JS divergence
- LSGAN (Least Squares GAN) - Pearson χ2 divergence
- f-GAN - Variational divergence minimization
- f-GANs
Integral Probability Metrics (IPM)
- WGAN - Wasserstein distance
- WGAN-GP - Gradient penalty, less capacity compromise
- McGAN - Mean and covariance matching
- Geometric GAN
- Fisher GAN - Chi-squared distance
Maximum Mean Discrepancy (MMD)
- GMMN
- MMD nets
-
CatGAN - Entropy of P(Y|X)
-
EBGAN - D(x) = ||Dec(Enc(x)) − x||
- LS-GAN (Loss-Sensitive GAN)
-
BEGAN - Wasserstein distance between the distribution of real/fake auto-encoder loss
-
AGE - $max_emin_g\Delta(e(g(Z))||Y)-\Delta(e(X)||Y)$ and encoder-generator reciprocity (bidirectional mapping)
- Softmax GAN
-
Cramér GAN - Cramér Distance
- LDGAN
- DRGAN - Vanilla GAN with gradient penalty
- Cramér GAN - Cramér Distance
- Regularized GAN
Lantern Space Disentangling
- InfoGAN - Unsupervised lantern space disentangling
- AcGAN - Supervised lantern space disentangling
Specifying Lantern Space Distribution
- AAE
- ALI, BiGAN - Match p(G(z),z) and q(x,E(x)), simultaneously learn an encoder and decoder
- AGE
- CatGAN
- SGAN - D outputs [CLASS-1, CLASS-2, . . . CLASS-N, FAKE]
- Improved GAN
- Triple-GAN
- Inception Score - Improved GAN
- FCN Score - pix2pix
- AMT Perceptual Studies - pix2pix
- Semantic Segmentation Metrics - CycleGAN
- FID, Precision, Recall and F1 Score - Are GANs Created Equal? A Large-Scale Study
Image-to-Image Translation
- DTN
- UNIT
- CoGAN
- CycleGAN, DiscoGAN, DualGAN
- Face Transfer with Generative Adversarial Network
- XGAN - Semantic consistency
- Scribbler
- pix2pix/PatchGAN
- PAN - Perceptual adversarial loss
- Context Encoder
- PAN
- SRGAN
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
- DTN
- UNIT
- CoGAN
- GAN-INT-CLS
- GAWWN
- StackGAN
- Adversarial Generation of Training Examples for Vehicle License Plate Recognition
- VAE/GAN - Visual attribute vectors
- CNAI
- DIAT
- Learning Residual Images for Face Attribute Manipulation
- IcGAN
- Age-cGAN
- CFGAN
- SL-GAN
- Fader Networks
- UNIT
- GeneGAN - Object transfiguration
- IAN
- Neural Face Editing with Intrinsic Image Disentangling
- Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
- ExprGAN
Face Frontalization/Profiling
- DR-GAN
- TP-GAN
- iGAN - Image manipulation
- TVSN - 3D view synthesis
- ID-CGAN - Image de-raining
- Perceptual GAN - Small object detection
- Create Anime Characters with A.I. !
- Generative Adversarial Networks: An Overview
- How Generative Adversarial Nets and its variants Work
- DeePSiM
- Unrooled GAN
- SGAN
- AM-GAN
- DeLiGAN - Mixture Gaussian prior distribution
- TTUR
gan-papers's People
Contributors
Watchers
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent