期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 7, 期 2, 页码 5326-5333出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3156176
关键词
Attention mechanism; computer vision for automation; deep learning methods; underwater image enhancement
类别
资金
- NationalNatural Science Foundation of China [61991413, U20A20200, 62073205]
- Youth Innovation Promotion Association of the Chinese Academy of Sciences [2019203]
In this study, we propose an adaptive learning attention network (LANet) to address the issues of color casts and low illumination in underwater images. The network incorporates techniques such as multiscale fusion module, parallel attention module, and adaptive learning module, as well as a multinomial loss function and asynchronous training mode, achieving excellent performance.
Underwater images suffer from color casts and low illumination due to the scattering and absorption of light as it propagates in water. These problems can interfere with underwater vision tasks, such as recognition and detection. We propose an adaptive learning attention network for underwater image enhancement based on supervised learning, named LANet, to solve these degradation issues. First, a multiscale fusion module is proposed to combine different spatial information. Second, we design a novel parallel attention module (PAM) to focus on the illuminated features and more significant color information coupled with the pixel and channel attention. Then, an adaptive learning module (ALM) can retain the shallow information and adaptively learn important feature information. Further, we utilize a multinomial loss function that is formed by mean absolute error and perceptual loss. Finally, we introduce an asynchronous training mode to promote the network's performance of multinomial loss function. Qualitative analysis and quantitative evaluations show the excellent performance of our method on different underwater datasets. The code is available at: https:// github.com/LiuShiBen/LANet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据