Multi-Process Training GAN for Identity-Preserving Face Synthesis
Recently, the advent of generative adversarial networks (GANs) in synthesizing identity-preserving faces has aroused the considerable interest of many scholars. However, face attribute representation learning, which is explicitly disentangled from identity feature and synthesizes identity-preserving...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8768064/ |
| _version_ | 1819078632621998080 |
|---|---|
| author | Zhiyong Tang Jianbing Yang Zhongcai Pei Xiao Song Baoshuang Ge |
| author_facet | Zhiyong Tang Jianbing Yang Zhongcai Pei Xiao Song Baoshuang Ge |
| author_sort | Zhiyong Tang |
| collection | DOAJ |
| description | Recently, the advent of generative adversarial networks (GANs) in synthesizing identity-preserving faces has aroused the considerable interest of many scholars. However, face attribute representation learning, which is explicitly disentangled from identity feature and synthesizes identity-preserving face images with high diversity and quality in other datasets, still remains challenging. To cope with that, this paper proposes multi-process training GAN, or MP-GAN for short, which significantly improves the disentangled representation, diversity, and quality. Unlike other existing single-process models that map noise to a final output resolution image in a single training process, MP-GAN divides training into multiple processes. The main idea is to first generate lower resolution images that contain lower frequency feature information through competition and then extract their disentangled facial features to generate a higher resolution image. Furthermore, an identity-preserving image with real identity feature and disentangled facial feature could be generated at the final output resolution training process. The distinct benefits are not only getting diverse facial feature generation but also achieving disentangled representation from the lower resolution training processes and rendering a photo-realistic image that contains high diversity but preserves identity at the final output resolution training process. The high performance of this method is highlighted by quantitative and qualitative comparisons. We conclude that MP-GAN can generate face images featuring high diversity and quality while efficiently preserving identity, thereby significantly outperforming most modern advanced methods. |
| first_indexed | 2024-12-21T19:16:11Z |
| format | Article |
| id | doaj.art-1490829652154fbca88d239aff88d834 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T19:16:11Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1490829652154fbca88d239aff88d8342022-12-21T18:53:04ZengIEEEIEEE Access2169-35362019-01-017976419765210.1109/ACCESS.2019.29302038768064Multi-Process Training GAN for Identity-Preserving Face SynthesisZhiyong Tang0Jianbing Yang1https://orcid.org/0000-0001-7710-5749Zhongcai Pei2Xiao Song3https://orcid.org/0000-0003-4279-426XBaoshuang Ge4School of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing, ChinaRecently, the advent of generative adversarial networks (GANs) in synthesizing identity-preserving faces has aroused the considerable interest of many scholars. However, face attribute representation learning, which is explicitly disentangled from identity feature and synthesizes identity-preserving face images with high diversity and quality in other datasets, still remains challenging. To cope with that, this paper proposes multi-process training GAN, or MP-GAN for short, which significantly improves the disentangled representation, diversity, and quality. Unlike other existing single-process models that map noise to a final output resolution image in a single training process, MP-GAN divides training into multiple processes. The main idea is to first generate lower resolution images that contain lower frequency feature information through competition and then extract their disentangled facial features to generate a higher resolution image. Furthermore, an identity-preserving image with real identity feature and disentangled facial feature could be generated at the final output resolution training process. The distinct benefits are not only getting diverse facial feature generation but also achieving disentangled representation from the lower resolution training processes and rendering a photo-realistic image that contains high diversity but preserves identity at the final output resolution training process. The high performance of this method is highlighted by quantitative and qualitative comparisons. We conclude that MP-GAN can generate face images featuring high diversity and quality while efficiently preserving identity, thereby significantly outperforming most modern advanced methods.https://ieeexplore.ieee.org/document/8768064/Multi-process trainingdisentangled representationdiversity and qualityidentity-preserving |
| spellingShingle | Zhiyong Tang Jianbing Yang Zhongcai Pei Xiao Song Baoshuang Ge Multi-Process Training GAN for Identity-Preserving Face Synthesis IEEE Access Multi-process training disentangled representation diversity and quality identity-preserving |
| title | Multi-Process Training GAN for Identity-Preserving Face Synthesis |
| title_full | Multi-Process Training GAN for Identity-Preserving Face Synthesis |
| title_fullStr | Multi-Process Training GAN for Identity-Preserving Face Synthesis |
| title_full_unstemmed | Multi-Process Training GAN for Identity-Preserving Face Synthesis |
| title_short | Multi-Process Training GAN for Identity-Preserving Face Synthesis |
| title_sort | multi process training gan for identity preserving face synthesis |
| topic | Multi-process training disentangled representation diversity and quality identity-preserving |
| url | https://ieeexplore.ieee.org/document/8768064/ |
| work_keys_str_mv | AT zhiyongtang multiprocesstrainingganforidentitypreservingfacesynthesis AT jianbingyang multiprocesstrainingganforidentitypreservingfacesynthesis AT zhongcaipei multiprocesstrainingganforidentitypreservingfacesynthesis AT xiaosong multiprocesstrainingganforidentitypreservingfacesynthesis AT baoshuangge multiprocesstrainingganforidentitypreservingfacesynthesis |