Score-Guided Generative Adversarial Networksopen access
- Authors
- Lee, Minhyeok; Seok, Junhee
- Issue Date
- Dec-2022
- Publisher
- MDPI
- Keywords
- generative adversarial network; image generation; image synthesis; GAN; generative model; Inception score; scoreGAN
- Citation
- AXIOMS, v.11, no.12
- Journal Title
- AXIOMS
- Volume
- 11
- Number
- 12
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69892
- DOI
- 10.3390/axioms11120701
- ISSN
- 2075-1680
2075-1680
- Abstract
- We propose a generative adversarial network (GAN) that introduces an evaluator module using pretrained networks. The proposed model, called a score-guided GAN (ScoreGAN), is trained using an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of the generator. Using another pretrained network instead of the Inception network, ScoreGAN circumvents overfitting of the Inception network such that the generated samples do not correspond to adversarial examples of the Inception network. In addition, evaluation metrics are employed only in an auxiliary role to prevent overfitting. When evaluated using the CIFAR-10 dataset, ScoreGAN achieved an Inception score of 10.36 +/- 0.15, which corresponds to state-of-the-art performance. To generalize the effectiveness of ScoreGAN, the model was evaluated further using another dataset, CIFAR-100. ScoreGAN outperformed other existing methods, achieving a Frechet Inception distance (FID) of 13.98.
- Files in This Item
-
- Appears in
Collections - College of ICT Engineering > School of Electrical and Electronics Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69892)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.