한국정보처리학회:학술대회논문집 (Proceedings of the Korea Information Processing Society Conference)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

의미적 손실 함수를 통한 Cycle GAN 성능 개선

Improved Cycle GAN Performance By Considering Semantic Loss

  • 정태영 (광운대학교 정보융합학부) ;
  • 이현식 (광운대학교 정보융합학부) ;
  • 엄예림 (광운대학교 정보융합학부) ;
  • 박경수 (광운대학교 정보융합학부) ;
  • 신유림 (서경대학교 시각디자인과) ;
  • 문재현 (한국기술거래사회)
  • Tae-Young Jeong (Dept. of Information Convergence, Kwang-Woon University) ;
  • Hyun-Sik Lee (Dept. of Information Convergence, Kwang-Woon University) ;
  • Ye-Rim Eom (Dept. of Information Convergence, Kwang-Woon University) ;
  • Kyung-Su Park (Dept. of Information Convergence, Kwang-Woon University) ;
  • Yu-Rim Shin (Dept. of Visual Design, Seo-Kyung University) ;
  • Jae-Hyun Moon (Korea Technology Transfer Agents Association)
  • 발행 : 2023.11.02
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Recently, several generative models have emerged and are being used in various industries. Among them, Cycle GAN is still used in various fields such as style transfer, medical care and autonomous driving. In this paper, we propose two methods to improve the performance of these Cycle GAN model. The ReLU activation function previously used in the generator was changed to Leaky ReLU. And a new loss function is proposed that considers the semantic level rather than focusing only on the pixel level through the VGG feature extractor. The proposed model showed quality improvement on the test set in the art domain, and it can be expected to be applied to other domains in the future to improve performance.

키워드