mlsanityData to 7 Oct 2026

Projected GANs Converge Faster

arXiv 2111.01007 ↗First posted 1 Nov 2021cs.CV cs.LGcited by 204

Not on the map. Why?

Cited by 60 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. Our Projected GAN improves image quality, sample efficiency, and convergence speed. It is further compatible with resolutions of up to one Megapixel and advances the state-of-the-art Fr'echet Inception Distance (FID) on twenty-two benchmark datasets. Importantly, Projected GANs match the previously lowest FIDs up to 40 times faster, cutting the wall-clock time from 5 days to less than 3 hours given the same computational resources.

Key facts. Cited by 204 papers in the map (data through 7 Oct 2026). Builds on 71 of its 95 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

71 of 95 references.

References · 71

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2014Going Deeper with Convolutionscited by 4,231
38 more
  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2018Deep contextualized word representationscited by 2,285
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  13. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  14. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  15. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  16. 2018Demystifying MMD GANscited by 1,268
  17. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  18. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  19. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  20. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  21. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  22. 2018Self-Attention Generative Adversarial Networkscited by 809
  23. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  24. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  25. 2018Which Training Methods for GANs do actually Converge?cited by 672
  26. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  27. 2018Do Better ImageNet Models Transfer Better?cited by 560
  28. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  29. 2018Assessing Generative Models via Precision and Recallcited by 401
  30. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  31. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  32. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  33. 2017Geometric GANcited by 232
  34. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  35. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  36. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  37. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  38. 2018Transferring GANs: generating images from limited datacited by 134

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 42; 2023: 57; 2024: 50; 2025: 26; 2026: 26.

204 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  4. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  5. 2023Adversarial Diffusion Distillationcited by 741
  6. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  7. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  8. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  9. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  10. 2023Improved Techniques for Training Consistency Modelscited by 430
  11. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  12. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
38 more
  1. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  2. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  3. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  4. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  5. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
  6. 2023Flow Matching in Latent Spacecited by 155
  7. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 148
  8. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  9. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  10. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  11. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  12. 2023GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesiscited by 84
  13. 2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
  14. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 76
  15. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 76
  16. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  17. 2023Diffusion Models Without Attentioncited by 75
  18. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  19. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 67
  20. 2022The ArtBench Dataset: Benchmarking Generative Models with Artworkscited by 64
  21. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  22. 2022Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learningcited by 57
  23. 2023Online Clustered Codebookcited by 55
  24. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 53
  25. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  26. 20233D generation on ImageNetcited by 47
  27. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
  28. 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesiscited by 45
  29. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  30. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  31. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  32. 2024Scaling Laws For Diffusion Transformerscited by 41
  33. 2024SF-V: Single Forward Video Generation Modelcited by 40
  34. 2022Novel Class Discovery without Forgettingcited by 39
  35. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  36. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  37. 2022Semi-Parametric Neural Image Synthesiscited by 36
  38. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36

50 most cited of 204 All 204 (JSON)