An embedded method: Improve the relevance of text and face image with enhanced face attributes

作者：

Highlights：

• Text-to-face image synthesis filed has strong application prospects.

• The proposed embedded method EFA strengths the model's learning of salient features.

• EFA can be embedded into different models to improve their performance.

• Verify the effectiveness and versatile of EFA by using the face dataset on 4 models.

摘要

•Text-to-face image synthesis filed has strong application prospects.•The proposed embedded method EFA strengths the model's learning of salient features.•EFA can be embedded into different models to improve their performance.•Verify the effectiveness and versatile of EFA by using the face dataset on 4 models.

论文关键词：Generative adversarial networks,Text-to-image face image generation,Face synthesis,Visual attributes

论文评审过程：Received 4 January 2022, Revised 20 June 2022, Accepted 3 July 2022, Available online 18 July 2022, Version of Record 28 July 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116815