A Novel Cross Channel Self-Attention based Approach for Facial Attribute Editing

• Meng Xu,
• Rize Jin,
• Liangfu Lu,
• Tae-Sun Chung,

Vol. 15, No. 6, June 30, 2021
10.3837/tiis.2021.06.010, Download Paper (Free):

• Generative Adversarial Network
• Cross Channel Self-Attention
• Image Translation
• Style Transfer
• Facial Attribute Editing

Abstract

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

Statistics

Cite this article