# LOGAN: Latent Optimisation for Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1912.00953 · HTML: https://mlsanity.com/paper/1912.00953/

## Key facts

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

## Built on by (most cited first, 30 of 42)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.06503/) (2022)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [Conditional Text Image Generation with Diffusion Models](https://mlsanity.com/paper/2306.10804/) (2023)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [StableIdentity: Inserting Anybody into Anywhere at First Sight](https://mlsanity.com/paper/2401.15975/) (2024)
- [Generative AI for Synthetic Data Generation: Methods, Challenges and the Future](https://mlsanity.com/paper/2403.04190/) (2024)
- [Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning](https://mlsanity.com/paper/2310.12952/) (2023)
- [A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion](https://mlsanity.com/paper/2207.03430/) (2022)
- [Intrinsic Dimension Estimation Using Wasserstein Distances](https://mlsanity.com/paper/2106.04018/) (2021)
- [Conditional GANs with Auxiliary Discriminative Classifier](https://mlsanity.com/paper/2107.10060/) (2021)
- [Class Balancing GAN with a Classifier in the Loop](https://mlsanity.com/paper/2106.09402/) (2021)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Joint inference and input optimization in equilibrium networks](https://mlsanity.com/paper/2111.13236/) (2021)
- [Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Model](https://mlsanity.com/paper/2305.03901/) (2023)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2112.01398/) (2021)
- [A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models](https://mlsanity.com/paper/2406.07451/) (2024)
- [Complex Momentum for Optimization in Games](https://mlsanity.com/paper/2102.08431/) (2021)
- [Exploring Gradient-based Multi-directional Controls in GANs](https://mlsanity.com/paper/2209.00698/) (2022)
- [Bring Metric Functions into Diffusion Models](https://mlsanity.com/paper/2401.02414/) (2024)
- [Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection](https://mlsanity.com/paper/2104.09261/) (2021)
- [A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture](https://mlsanity.com/paper/2210.11318/) (2022)

## 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.