Open joyhuang9473 opened 6 years ago
we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques.
we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator.
Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques.
All About the GANs(Generative Adversarial Networks) - Summarized lists for GAN https://github.com/hollobit/All-About-the-GAN
Data Augmentation in Emotion Classification Using Generative Adversarial Networks