dynamicd

1、动机

Different from the common image classification tasks where the training data remains fixed during the whole training process, GAN training appears to be time-varying since the synthesis quality of the generator is constantly evolving, as suggested in Fig. 1. That way, although the real data distribution keeps the same, the varying synthesis distribution still results in the change of the bi-classification task for the discriminator. It naturally raises a question: does a discriminator with a fixed capacity meet the demand of such a dynamic training environment?

2、主要方法

（1）基本方法：增大模型容量与减小模型容量

It also makes the bi-classification task change accordingly. Therefore, the capacity of discriminator required by the varying bi-classification task might be also different as training goes by.

A. Increasing capacity

If the bi-classification task becomes challenging while we have a weakdiscriminator, under-fitting would occur, such that a generator with the relatively low synthesis qualitycould easily fool the discriminator. We thus progressively increase the capacity of discriminator byincluding newly initialized neural filters every several iterations.

(2) Decreasing capacity

If the bi-classification task is relatively simple, a normal discriminator could also over-fit, which appears to memorize the training set. The synthesis quality would be thus deteriorated significantly. To mitigate this, we randomly eliminate a set of filters thus the layer width gradually shrinks, as shown on the right of Fig. 2.

（2）针对不同数据集的优化策略

基本出发点：limited training data leads to the over-fitting of discriminator while the enhanced discriminator could also benefit from the sufficient training samples.

NeurIPS2022：Improving GANs with A Dynamic Discriminator