mlsanityData to 7 Oct 2026

EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

arXiv 2111.15097 ↗First posted 30 Nov 2021cs.CV cs.LG cs.NEcited by 5

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying GAN architecture, it requires much expertise. Neural architecture search (NAS) has become an attractive solution to search GANs automatically. The early NAS-GANs search only generators to reduce search complexity but lead to a sub-optimal GAN. Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training. To alleviate the instability, we propose an efficient two-stage evolutionary algorithm-based NAS framework to search GANs, namely EAGAN. We decouple the search of G and D into two stages, where stage-1 searches G with a fixed D and adopts the many-to-one training strategy, and stage-2 searches D with the optimal G found in stage-1 and adopts the one-to-one training and weight-resetting strategies to enhance the stability of GAN training. Both stages use the non-dominated sorting method to produce Pareto-front architectures under multiple objectives (e.g., model size, Inception Score (IS), and Fr'echet Inception Distance (FID)). EAGAN is applied to the unconditional image generation task and can efficiently finish the search on the CIFAR-10 dataset in 1.2 GPU days. Our searched GANs achieve competitive results (IS=8.81±0.10, FID=9.91) on the CIFAR-10 dataset and surpass prior NAS-GANs on the STL-10 dataset (IS=10.44±0.087, FID=22.18). Source code: https://github.com/marsggbo/EAGAN.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

40 of 55 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  12. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
28 more
  1. 2016Least Squares Generative Adversarial Networkscited by 1,000
  2. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  3. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2017Wasserstein GANcited by 635
  6. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  7. 2017Progressive Neural Architecture Searchcited by 483
  8. 2019AutoML: A Survey of the State-of-the-Artcited by 388
  9. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  10. 2017Large-Scale Evolution of Image Classifierscited by 348
  11. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  12. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  13. 2017Hierarchical Representations for Efficient Architecture Searchcited by 188
  14. 2017Optimizing the Latent Space of Generative Networkscited by 157
  15. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  16. 2019CARS: Continuous Evolution for Efficient Neural Architecture Searchcited by 79
  17. 2020Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gapcited by 50
  18. 2018Evolutionary Generative Adversarial Networkscited by 42
  19. 2019AdversarialNAS: Adversarial Neural Architecture Search for GANscited by 38
  20. 2017Boundary-Seeking Generative Adversarial Networkscited by 27
  21. 2020Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Searchcited by 25
  22. 2018Improving MMD-GAN Training with Repulsive Loss Functioncited by 22
  23. 2020AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networkscited by 10
  24. 2019AGAN: Towards Automated Design of Generative Adversarial Networkscited by 8
  25. 2021Dynamically Grown Generative Adversarial Networkscited by 5
  26. 2019Coevolution of Generative Adversarial Networkscited by 4
  27. 2019The Six Fronts of the Generative Adversarial Networkscited by 3
  28. 2019DEGAS: Differentiable Efficient Generator Searchcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2023Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspectivecited by 11
  2. 2023EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learningcited by 6
  3. 2022NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimensioncited by 5
  4. 2024Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancementcited by 0
  5. 2026Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysiscited by 0