Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
Source abstract
Abstract
Neural Architecture Search (NAS) has emerged as a pivotal technique in optimizing the design of Generative Adversarial Networks (GANs), automating the search for effective architectures while addressing the challenges inherent in manual design. This paper provides a comprehensive review of NAS methods applied to GANs, categorizing and comparing various approaches based on criteria such as search strategies, evaluation metrics, and performance outcomes. The review highlights the benefits of NAS in improving GAN performance, stability, and efficiency, while also identifying limitations and areas for future research. Key findings include the superiority of evolutionary algorithms and gradient-based methods in certain contexts, the importance of robust evaluation metrics beyond traditional scores like Inception Score (IS) and Fréchet Inception Distance (FID), and the need for diverse datasets in assessing GAN performance. By presenting a structured comparison of existing NAS-GAN techniques, this paper aims to guide researchers in developing more effective NAS methods and advancing the field of GANs.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Generative Adversarial Networks and Image Synthesis · Digital Media Forensic Detection · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Computer Science, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia
Computer Science Department, College of Computer Science and Information Technology, Imam Abdulrahman bin Faisal University, Dammam 31441, Saudi Arabia
SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia
References (60)
Show source-provided references
1. A survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
2. Souza, L.A., Passos, L.A., Mendel, R., Ebigbo, A., Probst, A., Messmann, H., Palm, C., and Papa, J.P. (2021, January 7–9). Fine-tuning Generative Adversarial Networks using Metaheuristics. Proceedings of the Bildverarbeitung für die Medizin 2021, Regensburg, Germany.10.1007/978-3-658-33198-6_50 ↗
3. Advanced metaheuristic optimization techniques in applications of deep neural networks: A review10.1007/s00521-021-05960-5 ↗
4. Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review10.1007/s00259-022-05805-w ↗
5. GAN-based anomaly detection: A review10.1016/j.neucom.2021.12.093 ↗
6. Kocasari, U., Dirik, A., Tiftikci, M., and Yanardag, P. (2022, January 3–7). StyleMC: Multi-channel based fast text-guided image generation and manipulation. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACV51458.2022.00350 ↗
7. Mosolova, A.V., Fomin, V.V., and Bondarenko, I.Y. (2018, January 5–7). Text augmentation for neural networks. Proceedings of the CEUR Workshop Proceedings, Moscow, Russia.
8. Talbi, E.G. (2020). Optimization of deep neural networks: A survey and unified taxonomy. arXiv.
9. Thanh-Tung, H., and Tran, T. (2020, January 19–24). Catastrophic forgetting and mode collapse in GANs. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9207181 ↗
10. Neural architecture search: A survey
11. AutoML: A survey of the state-of-the-art10.1016/j.knosys.2020.106622 ↗
12. Gong, X., Chang, S., Jiang, Y., and Wang, Z. (November, January 27). AutoGAN: Neural architecture search for generative adversarial networks. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
13. Costa, V., Lourenço, N., Correia, J., and Machado, P. (2019, January 13–17). COEGAN: Evaluating the coevolution effect in generative adversarial networks. Proceedings of the Genetic and Evolutionary Computation Conference, Prague, Czech Republic.10.1145/3321707.3321746 ↗
14. AlphaGAN: Fully differentiable architecture search for generative adversarial networks10.1109/TPAMI.2021.3099829 ↗
15. Ganepola, V.V.V., and Wirasingha, T. (2021, January 5–7). Automating generative adversarial networks using neural architecture search: A review. Proceedings of the 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India.10.1109/ESCI50559.2021.9396991 ↗
16. Buthgamumudalige, V.U., and Wirasingha, T. (2021, January 11–13). Neural Architecture Search for Generative Adversarial Networks: A Review. Proceedings of the 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS), Negambo, Sri Lanka.10.1109/ICIAfS52090.2021.9605804 ↗
17. The application of evolutionary computation in generative adversarial networks (GANs): A systematic literature survey10.1007/s10462-024-10818-y ↗
18. Kang, J.-S., Kang, J., Kim, J.-J., Jeon, K.-W., Chung, H.-J., and Park, B.-H. (2023). Neural Architecture Search Survey: A Computer Vision Perspective. Sensors, 23.10.3390/s23031713 ↗
19. White, C., Safari, M., Sukthanker, R., Ru, B., Elsken, T., Zela, A., Dey, D., and Hutter, F. (2023). Neural architecture search: Insights from 1000 papers. arXiv.
20. Kitchenham, B. (2004). Procedures for Performing Systematic Reviews, Keele University. Technical report.
21. Talbi, E.G. (2009). Metaheuristics: From Design to Implementation, John Wiley & Sons.10.1002/9780470496916 ↗
22. Evolutionary generative adversarial networks10.1109/TEVC.2019.2895748 ↗
23. Al-Dujaili, A., Schmiedlechner, T., Hemberg, E., and O’Reilly, U.M. (2018). Towards distributed coevolutionary GANs. arXiv.
24. Toutouh, J., Hemberg, E., and O’Reilly, U.M. (2019, January 13–17). Spatial Evolutionary Generative Adversarial Networks. Proceedings of the Genetic and Evolutionary Computation Conference, Prague, Czech Republic.10.1145/3321707.3321860 ↗
25. Garciarena, U., Santana, R., and Mendiburu, A. (2018, January 15–19). Evolved GANs for generating pareto set approximations. Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’18, Kyoto, Japan.10.1145/3205455.3205550 ↗
26. Lu, Y., Kakillioglu, B., and Velipasalar, S. (2018). Autonomously and simultaneously refining deep neural network parameters by a bi-generative adversarial network aided genetic algorithm. arXiv.10.1109/ICIP.2019.8803539 ↗
27. Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7–12). 3D ShapeNets: A deep representation for volumetric shapes. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
28. Structure tuning method on deep convolutional generative adversarial network with nondominated sorting genetic algorithm II10.1002/cpe.5688 ↗
29. Evolutionary Architectural Search for Generative Adversarial Networks10.1109/TETCI.2021.3137377 ↗
30. Ying, G., He, X., Gao, B., Han, B., and Chu, X. EAGAN: Efficient two-stage evolutionary architecture search for GANs. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel, 23–27 October 2022.10.1007/978-3-031-19787-1_3 ↗
31. Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing10.1109/TEVC.2023.3338371 ↗
32. Kobayashi, M., and Nagao, T. (2020, January 8–12). A Multi-Objective Architecture Search for Generative Adversarial Networks. Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, Cancún, Mexico.10.1145/3377929.3390004 ↗
33. Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, MIT Press.
34. Wang, H., and Huan, J. (2019). AGAN: Towards automated design of generative adversarial networks. arXiv.
35. Searching Towards Class-Aware Generators for Conditional Generative Adversarial Networks10.1109/LSP.2022.3193589 ↗
36. Tian, Y., Wang, Q., Huang, Z., Li, W., Dai, D., Yang, M., Wang, J., and Fink, O. Off-policy reinforcement learning for efficient and effective gan architecture search. Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK, 23–28 August 2020, Proceedings, Part VII 16.10.1007/978-3-030-58571-6_11 ↗
37. Neural Architecture Search With a Lightweight Transformer for Text-to-Image Synthesis10.1109/TNSE.2022.3147787 ↗
38. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
39. Gao, C., Chen, Y., Liu, S., Tan, Z., and Yan, S. (2020, January 14–19). AdversarialNAS: Adversarial Neural Architecture Search for GANs. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00572 ↗
40. DEGAS: Differentiable efficient generator search10.1007/s00521-021-06309-8 ↗
41. Li, M., Lin, J., Ding, Y., Liu, Z., Zhu, J.Y., and Han, S. (2020, January 14–19). GAN Compression: Efficient Architectures for Interactive Conditional GANs. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00533 ↗
42. Differentiable Architecture Search with Attention Mechanisms for Generative Adversarial Networks10.1109/TETCI.2024.3369998 ↗
43. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016, January 5–10). Improved techniques for training gans. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.
44. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (July, January 26). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
45. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017, January 4–9). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
46. Real, E., Aggarwal, A., Huang, Y., and Le, Q.V. (February, January 27). Regularized evolution for image classifier architecture search. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
47. Tan, M., and Le, Q. (2019, January 9–15). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA.
48. Srivastava, A., Valkov, L., Russell, C., Gutmann, M.U., and Sutton, C. (2017, January 4–9). Veegan: Reducing mode collapse in gans using implicit variational learning. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
49. Mescheder, L., Geiger, A., and Nowozin, S. (2018, January 10–15). Which training methods for GANs do actually converge?. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden.
50. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–23). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
51. The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]10.1109/MSP.2012.2211477 ↗
52. Liu, Z., Luo, P., Wang, X., and Tang, X. (2015, January 7–13). Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.425 ↗
53. Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., and Xiao, J. (2015). Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv.
54. Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical report.
55. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
56. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
57. Uncover This Tech Term: Generative Adversarial Networks10.3348/kjr.2023.1306 ↗
58. Tanaka, F.H.K.D.S., and Aranha, C. (2019). Data augmentation using GANs. arXiv.
59. A Style-Based Generator Architecture for Generative Adversarial Networks10.1109/TPAMI.2020.2970919 ↗
60. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2018). Progressive growing of gans for improved quality, stability, and variation. arXiv.