SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
复制标题
DOI：
10.1109/tmm.2020.2975961
复制
发表时间：
2021-01-01
影响因子：
7.3
通讯作者：
Chinnam, Ratna Babu
中科院分区：
文献类型：
--
作者：
Emami, Hajar;Aliabadi, Majid Moradi;Chinnam, Ratna Babu
图像到图像的翻译是学习源域图像和目标域图像之间的映射。在本文中，我们将注意力机制直接引入到生成对抗网络（GAN）架构中，并提出了一种用于图像到图像翻译任务的新型空间注意力 GAN 模型（SPA-GAN）。 SPA-GAN 计算其鉴别器中的注意力，并使用它来帮助生成器更多地关注源域和目标域之间最具辨别力的区域，从而产生更真实的输出图像。我们还发现在 SPA-GAN 训练中引入额外的特征图损失有助于在翻译过程中保留领域特定的特征。与现有的注意力引导的 GAN 模型相比，SPA-GAN 是一种轻量级模型，不需要额外的注意力网络或监督。在基准数据集上与最先进的方法进行定性和定量比较，证明了 SPA-GAN 的卓越性能。
Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and propose a novel spatial attention GAN model (SPA-GAN) for image-to-image translation tasks. SPA-GAN computes the attention in its discriminator and use it to help the generator focus more on the most discriminative regions between the source and target domains, leading to more realistic output images. We also find it helpful to introduce an additional feature map loss in SPA-GAN training to preserve domain specific features during translation. Compared with existing attention-guided GAN models, SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.