Conditional generative adversarial networks (cGANs) have demonstrated
remarkable success due to their class-wise controllability and superior quality
for complex generation tasks. Typical cGANs solve the joint distribution
matching problem by decomposing two easier sub-problems: marginal matching and
conditional matching. From our toy experiments, we found that it is the best to
apply only conditional matching to certain samples due to the content-aware
optimization of the discriminator. This paper proposes a simple (a few lines of
code) but effective training methodology, selective focusing learning, which
enforces the discriminator and generator to learn easy samples of each class
rapidly while maintaining diversity. Our key idea is to selectively apply
conditional and joint matching for the data in each mini-batch. We conducted
experiments on recent cGAN variants in ImageNet (64x64 and 128x128), CIFAR-10,
and CIFAR-100 datasets, and improved the performance significantly (up to
35.18% in terms of FID) without sacrificing diversity.

本文提出使用选择性对焦学习的训练方法来解决条件生成对抗网络（cGANs）的训练问题，针对每个小批量的数据选择性地应用条件匹配和联合匹配，从而在 ImageNet、CIFAR-10 和 CIFAR-100 数据集上提高了 cGAN 的性能（FID 最高可达 35.18%），同时保持了多样性。