Abstract. Face attribute editing aims at editing the face image with
the given attribute. Most existing works employ Generative Adversarial Network (GAN) to operate face attribute editing. However, these
methods inevitably change the attribute-irrelevant regions, as shown in
Fig. 1. Therefore, we introduce the spatial attention mechanism into
GAN framework (referred to as SaGAN), to only alter the attributespeciic region and keep the rest unchanged. Our approach SaGAN consists of a generator and a discriminator. The generator contains an
attribute manipulation network (AMN) to edit the face image, and a
spatial attention network (SAN) to localize the attribute-speciic region
which restricts the alternation of AMN within this region. The discriminator endeavors to distinguish the generated images from the real ones,
and classify the face attribute. Experiments demonstrate that our approach can achieve promising visual results, and keep those attributeirrelevant regions unchanged. Besides, our approach can beneit the face
recognition by data augmentation