Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network

Simple item page
dc.contributor.authorLi, Hongyuen_US
dc.contributor.authorHan, Tianqien_US
dc.contributor.editorCignoni, Paolo and Miguel, Ederen_US
dc.date.accessioned2019-05-05T17:49:55Z
dc.date.available2019-05-05T17:49:55Z
dc.date.issued2019
dc.description.abstractIt is interesting to use an anime face as personal virtual image to replace the traditional sequence code. To generate diverse anime faces, this paper proposes a style-gender based anime GAN (SGA-GAN), where the gender is directly conditioned to ensure the gender differentiation, and style features serve as a condition to guarantee the style diversity. To extract style features, we train a style feature network (SFN) as a multi-task classifier to simultaneously fulfill gender classification, style classification, and image quality estimation. To make full use of available data, partly labeled or unlabeled, during the SFN training, we propose a label completion method to actively complete the missing gender or style labels. The active label completion is essentially a weakly-supervised learning process through ensembling three distinct classifiers to improve the generalization capability. Experiments verify that the active label completion can improve the model accuracy and the style feature as a condition can make better the diversity of generated anime faces.en_US
dc.description.sectionheadersLearning and Networks
dc.description.seriesinformationEurographics 2019 - Short Papers
dc.identifier.doi10.2312/egs.20191016
dc.identifier.issn1017-4656
dc.identifier.pages65-68
dc.identifier.urihttps://doi.org/10.2312/egs.20191016
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egs20191016
dc.publisherThe Eurographics Associationen_US
dc.titleTowards Diverse Anime Face Generation: Active Label Completion and Style Feature Networken_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
065-068.pdf
Size:
817.49 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
supplementary+file+for+algorithm.pdf
Size:
27.61 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
additional.gif
Size:
3.87 MB
Format:
Graphics Interchange Format
Download
Collections
EG 2019 - Short Papers