U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

25 Jul 2019Junho KimMinjae KimHyeonwoo KangKwanghee Lee

We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner. The attention module guides our model to focus on more important regions distinguishing between source and target domains based on the attention map obtained by the auxiliary classifier... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Image-to-Image Translation anime-to-selfie U-GAT-IT Kernel Inception Distance 11.52 # 1
Image-to-Image Translation selfie-to-anime U-GAT-IT Kernel Inception Distance 11.61 # 1