Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism
文献类型：期刊论文
| 作者 | M. F. Wu, T. J. Lan, X. C. Xue and X. W. Xu |
| 刊名 | Electronics
 |
| 出版日期 | 2023 |
| 卷号 | 12期号:8页码:25 |
| DOI | 10.3390/electronics12081887 |
| 英文摘要 | Low-light image enhancement is a crucial preprocessing task in complex vision tasks. It directly impacts object detection, image segmentation, and image recognition outcomes. In recent years, with the continuous development of deep learning techniques, an increasing number of image enhancement methods based on deep learning have emerged. However, due to the high cost of data collection and the limited content of supervised learning datasets, more and more scholars have shifted their focus to the field of unsupervised image enhancement. Unsupervised image enhancement methods do not require paired images of the same scene during the training process, which greatly reduces the threshold for network training. Nevertheless, current unsupervised methods still suffer from issues such as unstable enhancement effects and limited generalization ability. To address these problems, we propose an improved low-light image enhancement method. The proposed method employs the LSGAN as the training architecture and utilizes an attention map network to dynamically generate attention maps that best fit the network enhancement task, which can effectively improve the generalization ability and enhancement performance of the network. Additionally, we adopt an attention mechanism to enhance the subtle details of the image features. Regarding the network training, considering that the traditional convolutional neural network discriminator may not provide effective guidance to the generator in the early stages of training, we propose an improved discriminator structure. The experimental results demonstrate that our method can achieve good enhancement performance on different datasets and has practical value. Although our method has advantages in enhancing low-light images, it also has certain limitations, such as the network size not meeting the requirements for lightweight models and the potential for further improvement under extremely low-light conditions. We will strive to address these issues as comprehensively as possible in our future research. |
| URL标识 | 查看原文 |
| 语种 | 英语 |
| 源URL | [http://ir.ciomp.ac.cn/handle/181722/68028]  |
| 专题 | 中国科学院长春光学精密机械与物理研究所 |
| 推荐引用方式 GB/T 7714 | M. F. Wu, T. J. Lan, X. C. Xue and X. W. Xu. Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism[J]. Electronics,2023,12(8):25. |
| APA | M. F. Wu, T. J. Lan, X. C. Xue and X. W. Xu.(2023).Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism.Electronics,12(8),25. |
| MLA | M. F. Wu, T. J. Lan, X. C. Xue and X. W. Xu."Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism".Electronics 12.8(2023):25. |
入库方式： OAI收割
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。