用于图像到图像翻译的非对称GAN
Asymmetric GANs for Image-to-Image Translation
AI总结：
针对现有对称GAN图像翻译模型存在的双向不对等、模型易崩溃等问题，提出采用非对称架构和优化损失的AsymmetricGAN，在8个数据集的有监督和无监督任务中性能更优，为首款研究该类非对称结构的模型。
摘要：
现有的基于生成对抗网络（GANs）的无监督图像翻译模型可利用循环一致性损失学习从源域到目标域的映射。但这些方法始终采用对称网络架构来学习前向和后向循环。由于源域与目标域之间存在任务复杂度差异和循环输入差异，双向前向-后向循环翻译的不对等性十分显著，且两个域之间的信息量存在差异。本文分析了现有对称GAN在非对称翻译任务中的局限性，提出AsymmetricGAN模型，其翻译生成器和重建生成器尺寸不对等，且采用不同的参数共享策略，以适配无监督和有监督图像翻译任务中的非对称需求。此外，现有方法的训练阶段普遍存在模型崩溃问题，会降低生成图像的质量，因此我们探索了不同的优化损失以更好地训练AsymmetricGAN，使图像翻译具备更高的一致性和更好的稳定性。在8个数据集上开展的有监督和无监督生成任务的大量实验表明，与现有GAN相比，AsymmetricGAN实现了更优的模型容量和更好的生成性能。据我们所知，我们是首个在无监督和有监督图像翻译任务中研究非对称GAN结构的团队。
英文摘要：
Existing models for unsupervised image translation with Generative Adversarial Networks (GANs) can learn the mapping from the source domain to the target domain using a cycle-consistency loss. However, these 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 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 existing symmetric GANs 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 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, making image translation with higher consistency and better stability. Extensive experiments on both supervised and unsupervised generative tasks with 8 datasets show that AsymmetricGAN achieves superior model capacity and better generation performance compared with existing GANs. To the best of our knowledge, we are the first to investigate the asymmetric GAN structure on both unsupervised and supervised image translation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
