Unbalanced GANs: pre-training the generator of generative adversarial network using variational autoencoderUnbalanced GANs: 베이지안 오토인코더를 이용한 적대적 생성 신경망 사전 학습 방법론

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 126
  • Download : 0
In this paper, we propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network using variational autoencoder. By pre-training the generator, we prevent the discriminator's fast convergence at early epochs and show the generator's stabilized training. Furthermore, we improve the quality of the generated images through balancing the generator and the discriminator at early epochs. We apply our method to other GANs and find that Unbalanced GANs reduce mode collapses. We also show that Unbalanced GANs outperform VAE-GAN and ordinary GANs in terms of stabilized learning, faster convergence, and better image quality at early epochs.
Advisors
Kim, Daeyoungresearcher김대영researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iii, 32 p. :]

Keywords

Deep Learning▼aGenerative Model▼aGenerative Adversarial Network▼aVariational Autoencoder▼aTransfer Learning; 딥러닝▼a생성 모델▼a적대적 생성 신경망▼a베이지안 오토인코더▼a전이 학습

URI
http://hdl.handle.net/10203/296097
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948470&flag=dissertation
Appears in Collection
CS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0