Detailed Information
Cited 0 time in 
Cited 0 time in 
Cited 0 time in
Metadata Downloads
Performance Comparison of Autoencoders Using Multi-Head and Skipping Connections
- Authors
- Kim, Gyeongmin; Lee, Suyeon; Koh, Jinhwan
- Issue Date
- May-2024
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Autoencoder; Denoising; Image processing
- Citation
- Proceedings - 2024 RIVF International Conference on Computing and Communication Technologies, RIVF 2024, pp 247 - 249
- Pages
- 3
- Indexed
- SCOPUS
- Journal Title
- Proceedings - 2024 RIVF International Conference on Computing and Communication Technologies, RIVF 2024
- Start Page
- 247
- End Page
- 249
- Abstract
- 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 공학계열 > 전자공학과 > Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.