GANKIN: GENERATING KIN FACES USING DISENTANGLED GAN
Fady Saad Said Ghatas;
Abstract
Kin image generation from parents’ images is a high-level prediction and generation problem. This study presents a new method to predict and generate a kin face using parents’ faces, i.e. Tri-subject prediction or two-to-one prediction. We use a pipeline of unconditional GANs to overcome mode-collapse in conditional GANs. The model achieves promising results compared to the state-of-the-art, our model achieves a retrieval score of 0.19 versus 0.107 by the state-of-the-art. Our model is validated against SelfKin kinship verification model and achieved an accuracy of (63 % ± 7 %).
Other data
Title | GANKIN: GENERATING KIN FACES USING DISENTANGLED GAN | Other Titles | توليد وجوة الأبناء عن طريق فصل الخواص في شبكة الخصومة التوليدية | Authors | Fady Saad Said Ghatas | Issue Date | 2020 |
Attached Files
File | Size | Format | |
---|---|---|---|
BB1052.pdf | 603.07 kB | Adobe PDF | View/Open |
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.