Unsupervised multi-modal image translation based on the squeeze-and-excitation mechanism and feature attention module

• Published in: 高技术通讯（英文版） Vol. 30; no. 1; pp. 23 - 30
• Main Authors: HU Zhentao(胡振涛), HU Chonghao, YANG Haoran, SHUAI Weiwei
• Format: Journal Article
• Language: English
• Published: School of Artificial Intelligence,Henan University,Zhengzhou 450046,P.R.China%95795 Troops of the PLA,Guilin 541003,P.R.China 01.03.2024
• Subjects: feature attention(FA)module; multi-modal image translation; squeeze-and-excitation(SE)mechanism; generative adversarial network(GAN)
• ISSN: 1006-6748
• DOI: 10.3772/j.issn.1006-6748.2024.01.003

The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target do-main.However,the multi-generator mechanism is employed among the advanced approaches availa-ble to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-exci-tation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demon-strating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.