State-of-the-art models for unpaired image-to-image translation with Generative Adversarial Networks (GANs) can learn the mapping from the source domain to the target domain using a cycle-consistency loss. The intuition behind these models is that if we translate from one domain to the other and back again we should arrive at where we started. However, existing methods always adopt a symmetric network architecture to learn both forward and backward cycles. Because of the task complexity and cycle input difference between the source and target image domains, the inequality in bidirectional forward-backward cycle translations is significant and the amount of information between two domains is different. In this paper, we analyze the limitation of the existing symmetric GAN models in asymmetric translation tasks, and propose an AsymmetricGAN model with both translation and reconstruction generators of unequal sizes and different parameter-sharing strategy to adapt to the asymmetric need in both unsupervised and supervised image-to-image translation tasks. Moreover, the training stage of existing methods has the common problem of model collapse that degrades the quality of the generated images, thus we explore different optimization losses for better training of AsymmetricGAN, and thus make image-to-image translation with higher consistency and better stability. Extensive experiments on both supervised and unsupervised generative tasks with several publicly available datasets demonstrate that the proposed AsymmetricGAN achieves superior model capacity and better generation performance compared with existing GAN models. To the best of our knowledge, we are the first to investigate the asymmetric GAN framework on both unsupervised and supervised image-to-image translation tasks. The source code, data and trained models are available at https://github.com/Ha0Tang/AsymmetricGAN.

本文针对GAN模型在非对称翻译任务中的不足，提出了一种AsymmetricGAN模型，采用不对称大小和不同参数共享策略的翻译和重建生成器，以适应不对称需求，在无监督和有监督的图像翻译任务中，提出了不同的优化损失来提高AsymmetricGAN的训练效果和稳定性，并通过多个公开数据集的实验，证明了该模型比现有的GAN模型具有更强的模型能力和更好的生成效果。

用于图像翻译的非对称生成对抗网络