Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks

Understand

Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data.

• One natural remedy for this problem is data augmentation, which has been recently shown to be effective.
• However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions.
• In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning.