GIU-GANs:Global Information Utilization for Generative Adversarial Networks

doi:doi:10.57702/y5604wxl

GIU-GANs:Global Information Utilization for Generative Adversarial Networks

Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, because convolutions are limited by spatial-agnostic and channel-speciﬁc, features extracted by conventional GANs based on convolution are constrained. There-fore, GANs cannot capture in-depth details per image.

BibTex:

@dataset{Yongqi_Tian_and_Xueyuan_Gong_and_Jialin_Tang_and_Binghua_Su_and_Xiaoxiang_Liu_and_Xinyuan_Zhang_2024,
    abstract = {Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, because convolutions are limited by spatial-agnostic and channel-speciﬁc, features extracted by conventional GANs based on convolution are constrained. There-fore, GANs cannot capture in-depth details per image.},
    author = {Yongqi Tian and Xueyuan Gong and Jialin Tang and Binghua Su and Xiaoxiang Liu and Xinyuan Zhang},
    doi = {10.57702/y5604wxl},
    institution = {No Organization},
    keyword = {'Generative Adversarial Networks', 'Global Information Utilization', 'image generation'},
    month = {dec},
    publisher = {TIB},
    title = {GIU-GANs:Global Information Utilization for Generative Adversarial Networks},
    url = {https://service.tib.eu/ldmservice/dataset/giu-gans-global-information-utilization-for-generative-adversarial-networks},
    year = {2024}
}