方法证据记录
Semi-supervised GAN
Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Semi-supervised Generative Adversarial Network
分类方法记录 · ml-model / deep-learning
- Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29. · URL
- Odena, A. (2016). Semi-Supervised Learning with Generative Adversarial Networks. ICML Workshop on Generative Adversarial Networks. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。