Machine learningDeep learning / NLP / CV
迁移学习GAN
迁移学习GAN（Transfer Learning GAN）初始化一个生成对抗网络——或者其生成器和判别器——从在大型源数据集上预训练的权重开始，然后在较小的目标数据集上进行微调。这种方法通过重用大规模学习到的低级和中级特征表示，即使在目标域数据稀缺的情况下也能实现高质量的生成建模。
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.
来源
- Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems (NeurIPS), 27, 2672–2680. link ↗
- Wang, Y. & Ramanan, D. (2018). Transferring GANs: generating images from limited data. European Conference on Computer Vision (ECCV), 11205, 220–236. DOI: 10.1007/978-3-030-01231-1_14 ↗
如何引用本页
ScholarGate. (2026, June 3). Transfer Learning with Generative Adversarial Networks. ScholarGate. https://scholargate.app/zh/deep-learning/transfer-learning-gan
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.
- 域自适应GAN深度学习↔ compare
- 微调生成对抗网络深度学习↔ compare
- 生成对抗网络深度学习↔ compare
- 基于卷积神经网络的迁移学习深度学习↔ compare
- 扩散模型迁移学习深度学习↔ compare
- 变分自编码器深度学习↔ compare