상세 보기
Performance Comparison of Autoencoders Using Multi-Head and Skipping Connections
- Kim, Gyeongmin;
- Lee, Suyeon;
- Koh, Jinhwan
Citations
SCOPUS
0초록
This study introduces a novel Autoencoder design that enhances the conventional CNN-based Autoencoder architecture for more effective image noise reduction. By incorporating multi-head Autoencoders into the U-Net structure in a parallel configuration, this new architecture demonstrates approximately 1.25 times better Peak Signal-toNoise Ratio (PSNR) compared to traditional Autoencoders, proving its superior ability in reducing image noise. © 2024 IEEE.
키워드
Autoencoder; Denoising; Image processing
- 제목
- Performance Comparison of Autoencoders Using Multi-Head and Skipping Connections
- 저자
- Kim, Gyeongmin; Lee, Suyeon; Koh, Jinhwan
- 발행일
- 2024-05
- 유형
- Conference paper
- 저널명
- Proceedings - 2024 RIVF International Conference on Computing and Communication Technologies, RIVF 2024
- 페이지
- 247 ~ 249