R1 Regularization

Introduced by Mescheder et al. in Which Training Methods for GANs do actually Converge?

R$_{1}$ Regularization is a regularization technique and gradient penalty for training generative adversarial networks. It penalizes the discriminator from deviating from the Nash Equilibrium via penalizing the gradient on real data alone: when the generator distribution produces the true data distribution and the discriminator is equal to 0 on the data manifold, the gradient penalty ensures that the discriminator cannot create a non-zero gradient orthogonal to the data manifold without suffering a loss in the GAN game.

This leads to the following regularization term:

$$ R_{1}\left(\psi\right) = \frac{\gamma}{2}E_{p_{D}\left(x\right)}\left[||\nabla{D_{\psi}\left(x\right)}||^{2}\right] $$

Source: Which Training Methods for GANs do actually Converge?

Latest Papers

PAPER DATE
One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
| Christian BartzJoseph BethgeHaojin YangChristoph Meinel
2020-10-21
Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 Network
Jialu HuangJing LiaoSam Kwong
2020-10-12
Resolution Dependant GAN Interpolation for Controllable Image Synthesis Between Domains
Justin N. M. PinkneyDoron Adler
2020-10-11
MaterialGAN: Reflectance Capture using a Generative SVBRDF Model
Yu GuoCameron SmithMiloš HašanKalyan SunkavalliShuang Zhao
2020-09-30
PIE: Portrait Image Embedding for Semantic Control
Ayush TewariMohamed ElgharibMallikarjun B R.Florian BernardHans-Peter SeidelPatrick PérezMichael ZollhöferChristian Theobalt
2020-09-20
MIPGAN -- Generating Robust and High Quality Morph Attacks Using Identity Prior Driven GAN
Haoyu ZhangSushma VenkateshRaghavendra RamachandraKiran RajaNaser DamerChristoph Busch
2020-09-03
GIF: Generative Interpretable Faces
| Partha GhoshPravir Singh GuptaRoy UzielAnurag RanjanMichael BlackTimo Bolkart
2020-08-31
DeepLandscape: Adversarial Modeling of Landscape Video
Elizaveta LogachevaRoman SuvorovOleg KhomenkoAnton MashikhinVictor Lempitsky
2020-08-21
Improving the Performance of Fine-Grain Image Classifiers via Generative Data Augmentation
Shashank ManjunathAitzaz NathanielJeff DruceStan German
2020-08-12
StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows
Rameen AbdalPeihao ZhuNiloy MitraPeter Wonka
2020-08-06
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
Elad RichardsonYuval AlalufOr PatashnikYotam NitzanYaniv AzarStav ShapiroDaniel Cohen-Or
2020-08-03
Detection, Attribution and Localization of GAN Generated Images
Michael GoebelLakshmanan NatarajTejaswi NanjundaswamyTajuddin Manhar MohammedShivkumar ChandrasekaranB. S. Manjunath
2020-07-20
Generative Hierarchical Features from Synthesizing Images
| Yinghao XuYujun ShenJiapeng ZhuCeyuan YangBolei Zhou
2020-07-20
Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? -- Vulnerability and Detection
Sushma VenkateshHaoyu ZhangRaghavendra RamachandraKiran RajaNaser DamerChristoph Busch
2020-07-07
A Free Viewpoint Portrait Generator with Dynamic Styling
| Anpei ChenRuiyang LiuLing XieJingyi Yu
2020-07-07
Collaborative Learning for Faster StyleGAN Embedding
Shanyan GuanYing TaiBingbing NiFeida ZhuFeiyue HuangXiaokang Yang
2020-07-03
PriorGAN: Real Data Prior for Generative Adversarial Nets
Shuyang GuJianmin BaoDong ChenFang Wen
2020-06-30
High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images
Stephan J. GarbinMarek KowalskiMatthew JohnsonJamie Shotton
2020-06-26
Differentiable Augmentation for Data-Efficient GAN Training
| Shengyu ZhaoZhijian LiuJi LinJun-Yan ZhuSong Han
2020-06-18
Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems
Huy H. NguyenJunichi YamagishiIsao EchizenSébastien Marcel
2020-06-15
Training Generative Adversarial Networks with Limited Data
| Tero KarrasMiika AittalaJanne HellstenSamuli LaineJaakko LehtinenTimo Aila
2020-06-11
Rényi Generative Adversarial Networks
Himesh BhatiaWilliam PaulFady AlajajiBahman GharesifardPhilippe Burlina
2020-06-03
Using Generative Models for Pediatric wbMRI
Alex ChangVinith M. SuriyakumarAbhishek MoturuNipaporn TewattanaratAndrea DoriaAnna Goldenberg
2020-06-01
Network Bending: Manipulating The Inner Representations of Deep Generative Models
| Terence BroadFrederic Fol LeymarieMick Grierson
2020-05-25
Recognizing Families through Images with Pretrained Encoder
Tuan-Duy H. NguyenHuu-Nghia H. NguyenHieu Dao
2020-05-24
Face Identity Disentanglement via Latent Space Mapping
Yotam NitzanAmit BermanoYangyan LiDaniel Cohen-Or
2020-05-15
Editing in Style: Uncovering the Local Semantics of GANs
| Edo CollinsRaja BalaBob PriceSabine Süsstrunk
2020-04-29
Adversarial Latent Autoencoders
| Stanislav PidhorskyiDonald AdjerohGianfranco Doretto
2020-04-09
Feature Quantization Improves GAN Training
| Yang ZhaoChunyuan LiPing YuJianfeng GaoChangyou Chen
2020-04-05
StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
Ayush TewariMohamed ElgharibGaurav BharajFlorian BernardHans-Peter SeidelPatrick PérezMichael ZollhöferChristian Theobalt
2020-03-31
One-Shot Domain Adaptation For Face Generation
Chao YangSer-Nam Lim
2020-03-28
Re-Training StyleGAN -- A First Step Towards Building Large, Scalable Synthetic Facial Datasets
Viktor VarkarakisShabab BazrafkanPeter Corcoran
2020-03-24
Perceptual Image Super-Resolution with Progressive Adversarial Network
Lone WongDeli ZhaoShaohua WanBo Zhang
2020-03-08
StyleGAN2 Distillation for Feed-forward Image Manipulation
| Yuri ViazovetskyiVladimir IvashkinEvgeny Kashin
2020-03-07
Semi-Supervised StyleGAN for Disentanglement Learning
Weili NieTero KarrasAnimesh GargShoubhik DebnathAnjul PatneyAnkit B. PatelAnima Anandkumar
2020-03-06
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
| Sangwoo MoMinsu ChoJinwoo Shin
2020-02-25
HRFA: High-Resolution Feature-based Attack
| Zhixing YeSizhe ChenPeidong ZhangChengjin SunXiaolin Huang
2020-01-21
Unsupervised multi-modal Styled Content Generation
Omry SendikDani LischinskiDaniel Cohen-Or
2020-01-10
CNN-generated images are surprisingly easy to spot... for now
| Sheng-Yu WangOliver WangRichard ZhangAndrew OwensAlexei A. Efros
2019-12-23
Unconstrained Facial Expression Transfer using Style-based Generator
| Chao YangSer-Nam Lim
2019-12-12
Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations
Sven GowalChongli QinPo-Sen HuangTaylan CemgilKrishnamurthy DvijothamTimothy MannPushmeet Kohli
2019-12-06
Analyzing and Improving the Image Quality of StyleGAN
| Tero KarrasSamuli LaineMiika AittalaJanne HellstenJaakko LehtinenTimo Aila
2019-12-03
Detecting GAN generated errors
Xiru ZhuFengdi CheTianzi YangTzuyang YuDavid MegerGregory Dudek
2019-12-02
Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
| Ceyuan YangYujun ShenBolei Zhou
2019-11-21
Unsupervised Projection Networks for Generative Adversarial Networks
Daiyaan ArfeenJesse Zhang
2019-09-30
RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis
| Atsuhiro NoguchiTatsuya Harada
2019-09-27
LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks
| Cedric OeldorfGerasimos Spanakis
2019-09-22
Generating High-Resolution Fashion Model Images Wearing Custom Outfits
Gökhan YildirimNikolay JetchevRoland VollgrafUrs Bergmann
2019-08-23
Image Synthesis From Reconfigurable Layout and Style
| Wei SunTianfu Wu
2019-08-20
Emergence of Object Segmentation in Perturbed Generative Models
| Adam BielskiPaolo Favaro
2019-05-29
Improved Precision and Recall Metric for Assessing Generative Models
| Tuomas KynkäänniemiTero KarrasSamuli LaineJaakko LehtinenTimo Aila
2019-04-15
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
| Rameen AbdalYipeng QinPeter Wonka
2019-04-05
A Style-Based Generator Architecture for Generative Adversarial Networks
| Tero KarrasSamuli LaineTimo Aila
2018-12-12
Which Training Methods for GANs do actually Converge?
| Lars MeschederAndreas GeigerSebastian Nowozin
2018-01-13

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories