SPA-GAN: Spatial Attention GAN for Image-to-Image Translation
This is an incremental improvement for image-to-image translation tasks, offering a lightweight model without extra networks.
The paper tackled image-to-image translation by proposing SPA-GAN, a spatial attention GAN that integrates attention into the discriminator to focus on discriminative regions, resulting in more realistic images with superior performance on benchmarks.
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.