生成对抗网络（GAN）评估指标

这部分内容有帮助吗？

参考文献

Generative Adversarial Networks, Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014 Advances in Neural Information Processing Systems DOI: 10.48550/arXiv.1406.2661 - 这篇开创性论文介绍了生成对抗网络及其对抗训练框架，对于理解GAN评估的内在机制至关重要。
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Sepp Hochreiter, 2017 Advances in Neural Information Processing Systems, Vol. 30 (Neural Information Processing Systems Foundation, Inc. (NeurIPS)) DOI: 10.5555/3295222.3295293 - 本文提出了Fréchet Inception Distance (FID)，这是一个广泛使用且重要的指标，用于评估GAN生成的图像质量和多样性。
Improved Precision and Recall Metric for Assessing Generative Models, Tuomas Kynkäänniemi, Tero Karras, Samuli Laine, Jaakko Lehtinen, Timo Aila, 2019 Advances in Neural Information Processing Systems, Vol. 32 (Neural Information Processing Systems Foundation) DOI: 10.48550/arXiv.1904.06991 - 该论文提出了一种改进的Precision和Recall指标，用于评估生成模型，为判别数据保真度和多样性以及诊断模式崩溃等问题提供了特定见解。
Wasserstein GAN, Martin Arjovsky, Soumith Chintala, Léon Bottou, 2017 Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 DOI: 10.5555/3305890.3305953 - 本文介绍了Wasserstein GAN，它解决了GAN训练中的稳定性问题和模式崩溃，为理解和诊断GAN收敛及故障模式提供了重要背景。