mlsanityData to 7 Oct 2026

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

arXiv 2301.12811 ↗First posted 30 Jan 2023cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) learn a target probability distribution by optimizing a generator and a discriminator with minimax objectives. This paper addresses the question of whether such optimization actually provides the generator with gradients that make its distribution close to the target distribution. We derive metrizable conditions, sufficient conditions for the discriminator to serve as the distance between the distributions by connecting the GAN formulation with the concept of sliced optimal transport. Furthermore, by leveraging these theoretical results, we propose a novel GAN training scheme, called slicing adversarial network (SAN). With only simple modifications, a broad class of existing GANs can be converted to SANs. Experiments on synthetic and image datasets support our theoretical results and the SAN's effectiveness as compared to usual GANs. Furthermore, we also apply SAN to StyleGAN-XL, which leads to state-of-the-art FID score amongst GANs for class conditional generation on ImageNet 256×256. Our implementation is available on https://ytakida.github.io/san.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 67 of its 94 references that are in the map. First posted on arXiv 30 Jan 2023.

Builds on

67 of 94 references.

References · 67

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  11. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
38 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2017Improved Training of Wasserstein GANscited by 2,223
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  9. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  10. 2018Self-Attention Generative Adversarial Networkscited by 809
  11. 2018Which Training Methods for GANs do actually Converge?cited by 672
  12. 2017Wasserstein GANcited by 635
  13. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  14. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  15. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  16. 2018Invertible Residual Networkscited by 364
  17. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  18. 2018cGANs with Projection Discriminatorcited by 253
  19. 2017Geometric GANcited by 232
  20. 2018Adversarial Audio Synthesiscited by 222
  21. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  22. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  23. 2019Generalized Sliced Wasserstein Distancescited by 205
  24. 2021Projected GANs Converge Fastercited by 204
  25. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  26. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  27. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  28. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 118
  29. 2017The Numerics of GANscited by 104
  30. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  31. 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
  32. 2020Distributional Sliced-Wasserstein and Applications to Generative Modelingcited by 69
  33. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  34. 2017Gradient descent GAN optimization is locally stablecited by 65
  35. 2019Reducing Noise in GAN Training with Variance Reduced Extragradientcited by 61
  36. 2021Variational Wasserstein gradient flowcited by 53
  37. 2018On the Convergence and Robustness of Training GANs with Regularized Optimal Transportcited by 51
  38. 2018Finding Mixed Nash Equilibria of Generative Adversarial Networkscited by 48

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 5; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  2. 2024Flow Generator Matchingcited by 26
  3. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  4. 2023Diffusion Models with Deterministic Normalizing Flow Priorscited by 7
  5. 2023BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Networkcited by 6
  6. 2025Neon: Negative Extrapolation From Self-Training Improves Image Generationcited by 5
  7. 2025Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)cited by 4
  8. 2024Solving Prior Distribution Mismatch in Diffusion Models via Optimal Transportcited by 2
  9. 2023Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overviewcited by 1
  10. 2025Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversitycited by 1
  11. 2025VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registrationcited by 0
  12. 2025SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminatorcited by 0
2 more
  1. 2026Pairing Regularization for Mitigating Many-to-One Collapse in GANscited by 0
  2. 2026Improving Generative Adversarial Networks with Self-Distillationcited by 0