Proceedings of the Korea Information Processing Society Conference (한국정보처리학회:학술대회논문집)
- 2023.05a
- /
- Pages.527-529
- /
- 2023
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
A Study on Auction-Inspired Multi-GAN Training
경매 메커니즘을 이용한 다중 적대적 생성 신경망 학습에 관한 연구
- Joo Yong Shim (Dept. of Electrical and Computer Engineering, Korea University) ;
- Jean Seong Bjorn Choe (Dept. of Electrical and Computer Engineering, Korea University) ;
- Jong-Kook Kim (Dept. of Electrical and Computer Engineering, Korea University)
- Published : 2023.05.18
Abstract
Generative Adversarial Networks (GANs) models have developed rapidly due to the emergence of various variation models and their wide applications. Despite many recent developments in GANs, mode collapse, and instability are still unresolved issues. To address these problems, we focused on the fact that a single GANs model itself cannot realize local failure during the training phase without external standards. This paper introduces a novel training process involving multiple GANs, inspired by auction mechanisms. During the training, auxiliary performance metrics for each GANs are determined by the others through the process of various auction methods.
Keywords