GRA-GAN: Generative adversarial network for image style transfer of Gender, Race, and age

•Generating gender, age, and race images based on information fusion in GRA-GAN.•Element-wise multiplication of the image gradient is performed in the decoder.•Unidirectional training was configured for forward and backward directions.•For training, fusing the race and gender tasks, and configuring...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expert systems with applications Jg. 198; S. 116792
Hauptverfasser: Kim, Yu Hwan, Nam, Se Hyun, Hong, Seung Baek, Park, Kang Ryoung
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Elsevier Ltd 15.07.2022
Elsevier BV
Schlagworte:
Age
Age estimation and classification of race and gender
Channel-wise and multiplication-based information fusion of encoder and decoder features
Chronology
Coders
Data integration
Facial image transformation
Gender
Generative adversarial networks
GRA-GAN
Multiplication
Object recognition
Race
Facial image transformation
Age estimation and classification of race and gender
GRA-GAN
Channel-wise and multiplication-based information fusion of encoder and decoder features
ISSN:0957-4174, 1873-6793
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Generating gender, age, and race images based on information fusion in GRA-GAN.•Element-wise multiplication of the image gradient is performed in the decoder.•Unidirectional training was configured for forward and backward directions.•For training, fusing the race and gender tasks, and configuring reference age loss.•Our trained model are publicly available. Despite a large amount of available data, the datasets that have been recently used in studies on age estimation still entail the age class imbalance problem owing to different age distributions of race or gender. This results in overfitting in which training data aligns toward one side and ultimately reduces the generality of age estimation. Same problems can occur in the cases of race and gender recognition. This problem can be solved if age images that were insufficient in a previously trained distribution or race and gender information that was not considered in the previously trained distribution can be newly created as images that are identical to the previously trained distribution. Therefore, we propose a race, age, and gender image transformation technique by a generative adversarial network for image style transfer of gender, race, and age (GRA-GAN) based on channel-wise and multiplication-based information fusion of encoder and decoder features. Experiments using four open databases (MORPH, AAF, AFAD, and UTK) indicated that our method outperformed the state-of-the-art methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2022.116792