模式识别与人工智能
Sunday, Apr. 6, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2023, Vol. 36 Issue (5): 407-418    DOI: 10.16451/j.cnki.issn1003-6059.202305002
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Underwater Image Enhancement Network Based on Visual Multi-head Attention and Skip-Layer Whitening
CONG Xiaofeng1, GUI Jie1,2, HE Lei2, ZHANG Jun3
1. School of Cyber Science and Engineering, Southeast University, Nanjing 211189;
2. Purple Mountain Laboratories, Nanjing 211189;
3. School of Artificial Intelligence, Anhui University, Hefei 230039

Download: PDF (4935 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Due to the phenomena of light absorption and scattering, as well as the presence of small particles in underwater environment, underwater images suffer from the problems of color imbalance and detail distortion. To address this issue, an underwater image enhancement network based on visual multi-head attention and skip-layer whitening is proposed in this paper. A hierarchical architecture is adopted, feature extraction is performed by the encoding path and image reconstruction is carried out by the decoding path. The main components of the encoding and decoding paths are visual multi-head self-attention blocks. Instance whitening is applied to shallow features. The features of shallow layer after instance whitening are embedded into the features of deep layer by skip-layer connection as skip-layer whitening path. Content loss and structure loss are employed in the training process of the proposed network. The comparative experiment on benchmark underwater image datasets demonstrates the effectiveness of visual multi-head self-attention and instance whitening for underwater enhancement task, both quantitatively and visually.
Key wordsUnderwater Imaging      Visual Attention      Skip-Layer Whitening      Quality Restoration     
Received: 16 March 2023     
ZTFLH: TP391  
Fund:National Natural Science Foundation of China(No.62172090), Start-up Research Fund of Southeast University(No.RF1028623097)
Corresponding Authors: ZHANG Jun, Ph.D., professor. His research interests include computer vision and pattern recognition.   
About author:: CONG Xiaofeng, Ph.D. candidate. His research interests include underwater image enhancement and image dehazing.GUI Jie, Ph.D., professor. His research interests include generative algorithm, image dehazing and self-supervised learning.HE Lei, Ph.D., associate professor. His research interests include cyberspace security and endogenous safety.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CONG Xiaofeng
GUI Jie
HE Lei
ZHANG Jun
Cite this article:   
CONG Xiaofeng,GUI Jie,HE Lei等. Underwater Image Enhancement Network Based on Visual Multi-head Attention and Skip-Layer Whitening[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(5): 407-418.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202305002      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2023/V36/I5/407
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn