mlsanityData to 7 Oct 2026

GLeaD: Improving GANs with A Generator-Leading Task

arXiv 2212.03752 ↗First posted 7 Dec 2022cs.CV eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate whether an image comes from real data or is produced by G. Under such a formulation, D plays as the rule maker and hence tends to dominate the competition. Towards a fairer game in GANs, we propose a new paradigm for adversarial training, which makes G assign a task to D as well. Specifically, given an image, we expect D to extract representative features that can be adequately decoded by G to reconstruct the input. That way, instead of learning freely, D is urged to align with the view of G for domain classification. Experimental results on various datasets demonstrate the substantial superiority of our approach over the baselines. For instance, we improve the FID of StyleGAN2 from 4.30 to 2.55 on LSUN Bedroom and from 4.04 to 2.82 on LSUN Church. We believe that the pioneering attempt present in this work could inspire the community with better designed generator-leading tasks for GAN improvement.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 69 of its 79 references that are in the map. First posted on arXiv 7 Dec 2022.

Builds on

69 of 79 references.

References · 69

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
38 more
  1. 2017Improved Training of Wasserstein GANscited by 2,223
  2. 2014Conditional Generative Adversarial Netscited by 2,152
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  7. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  8. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  9. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  10. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  11. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  12. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  13. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  14. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  15. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  16. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  17. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  18. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  19. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  20. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  21. 2021GAN Inversion: A Surveycited by 366
  22. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  23. 2016Adversarial Feature Learningcited by 350
  24. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  25. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  26. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  27. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  28. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  29. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  30. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  31. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  32. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 177
  33. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  34. 2020Adversarial Latent Autoencoderscited by 155
  35. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  36. 2016Inverting The Generator Of A Generative Adversarial Networkcited by 140
  37. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  38. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2023Revisiting the Evaluation of Image Synthesis with GANscited by 7
  2. 2023Learning Modulated Transformation in GANscited by 1
  3. 2024Rethinking Image Skip Connections in StyleGAN2cited by 1
  4. 2026HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistencycited by 0