Machine learning
生成对抗网络
生成对抗网络（Generative Adversarial Network, GAN）由 Ian Goodfellow 及其同事于 2014 年提出，它通过两个神经网络——生成器和判别器——的竞争来生成逼真的合成数据。GAN 被广泛用于图像合成、数据增强和分布估计。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+20 more
来源
- Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗
- Karras, T. et al. (2020). Analyzing and Improving the Image Quality of StyleGAN. CVPR. DOI: 10.1109/CVPR42600.2020.00813 ↗
如何引用本页
ScholarGate. (2026, June 1). Generative Adversarial Network (GAN). ScholarGate. https://scholargate.app/zh/deep-learning/generative-adversarial-network
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →被引用于
对抗训练CycleGAN：具有循环一致性的非配对图像到图像翻译域自适应GAN域自适应变分自编码器可解释生成对抗网络微调生成对抗网络LoRA 和 PEFT多语言生成对抗网络 (Multilingual GAN)多模态生成对抗网络多模态变分自编码器神经风格迁移自监督扩散模型自监督生成对抗网络自监督图像分类自监督变分自编码器半监督扩散模型Semi-supervised GAN半监督变分自编码器用于披露控制的合成数据生成迁移学习GAN迁移学习与变分自编码器变分自编码器Vision Transformer瓦瑟施泰因生成对抗网络 (WGAN)弱监督扩散模型弱监督生成对抗网络 (Weakly Supervised GAN)弱监督变分自编码器