• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

A Novel Cross Channel Self-Attention based Approach for 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 Fr├ęchet 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

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
M. Xu, R. Jin, L. Lu and T. Chung, "A Novel Cross Channel Self-Attention based Approach for Facial Attribute Editing," KSII Transactions on Internet and Information Systems, vol. 15, no. 6, pp. 2115-2127, 2021. DOI: 10.3837/tiis.2021.06.010.

[ACM Style]
Meng Xu, Rize Jin, Liangfu Lu, and Tae-Sun Chung. 2021. A Novel Cross Channel Self-Attention based Approach for Facial Attribute Editing. KSII Transactions on Internet and Information Systems, 15, 6, (2021), 2115-2127. DOI: 10.3837/tiis.2021.06.010.