MetaGAN: An Adversarial Approach to Few-Shot Learning

Ruixiang ZHANG, Tong Che, Zoubin Ghahramani, Yoshua Bengio, Yangqiu Song

Neural Information Processing Systems 

We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found