mlsanityData to 14 Oct 2026

LOGAN: Latent Optimisation for Generative Adversarial Networks

arXiv 1912.00953 ↗First posted 2 Dec 2019cs.LG stat.MLcited by 42

Not on the map. Why?

Abstract (arXiv)

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we improve CS-GAN with natural gradient-based latent optimisation and show that it improves adversarial dynamics by enhancing interactions between the discriminator and the generator. Our experiments demonstrate that latent optimisation can significantly improve GAN training, obtaining state-of-the-art performance for the ImageNet (128 × 128) dataset. Our model achieves an Inception Score (IS) of 148 and an Fr'echet Inception Distance (FID) of 3.4, an improvement of 17% and 32% in IS and FID respectively, compared with the baseline BigGAN-deep model with the same architecture and number of parameters.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 9; 2023: 7; 2024: 6; 2025: 1; 2026: 1.

42 papers.

Sort:

By area:

  1. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  4. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  5. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 276
  6. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  7. 2021Is Attention Better Than Matrix Decomposition?cited by 77
  8. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 64
  9. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  10. 2023Conditional Text Image Generation with Diffusion Modelscited by 58
  11. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  12. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
30 more
  1. 2024StableIdentity: Inserting Anybody into Anywhere at First Sightcited by 35
  2. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Futurecited by 33
  3. 2023Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learningcited by 24
  4. 2022A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completioncited by 23
  5. 2021Intrinsic Dimension Estimation Using Wasserstein Distancescited by 20
  6. 2021Conditional GANs with Auxiliary Discriminative Classifiercited by 20
  7. 2021Class Balancing GAN with a Classifier in the Loopcited by 17
  8. 2021Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reductioncited by 17
  9. 2021Joint inference and input optimization in equilibrium networkscited by 15
  10. 2023Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Modelcited by 14
  11. 2021Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networkscited by 13
  12. 2021TISE: Bag of Metrics for Text-to-Image Synthesis Evaluationcited by 13
  13. 2024A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Modelscited by 13
  14. 2021Complex Momentum for Optimization in Gamescited by 11
  15. 2022Exploring Gradient-based Multi-directional Controls in GANscited by 10
  16. 2024Bring Metric Functions into Diffusion Modelscited by 7
  17. 2021Latent-Optimized Adversarial Neural Transfer for Sarcasm Detectioncited by 6
  18. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  19. 2023Adversarial Latent Autoencoder with Self-Attention for Structural Image Synthesiscited by 5
  20. 2024Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns Injectioncited by 5
  21. 2025The Vendiscope: An Algorithmic Microscope For Data Collectionscited by 5
  22. 2022Reducing Training Sample Memorization in GANs by Training with Memorization Rejectioncited by 4
  23. 2024Compress Guidance in Conditional Diffusion Samplingcited by 4
  24. 2026Stroke of Surprise: Progressive Semantic Illusions in Vector Sketchingcited by 3
  25. 2023NaturalFinger: Generating Natural Fingerprint with Generative Adversarial Networkscited by 2
  26. 2023Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerabilitycited by 2
  27. 2021Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translationcited by 1
  28. 2021Generative Flows as a General Purpose Solution for Inverse Problemscited by 1
  29. 2021Unrealistic Feature Suppression for Generative Adversarial Networkscited by 0
  30. 2022A Review of the Convergence of 5G/6G Architecture and Deep Learningcited by 0