Multi-task learning with self-learning weight for image denoising
Abstract Background Image denoising technology removes noise from the corrupted image by utilizing different features between image and noise. Convolutional neural network (CNN)-based algorithms have been the concern of the recent progress on diverse image restoration problems and become an efficien...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-04-01
|
| Series: | Journal of Engineering and Applied Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s44147-024-00425-7 |
| _version_ | 1827277136111599616 |
|---|---|
| author | Qian Xiang Yong Tang Xiangyang Zhou |
| author_facet | Qian Xiang Yong Tang Xiangyang Zhou |
| author_sort | Qian Xiang |
| collection | DOAJ |
| description | Abstract Background Image denoising technology removes noise from the corrupted image by utilizing different features between image and noise. Convolutional neural network (CNN)-based algorithms have been the concern of the recent progress on diverse image restoration problems and become an efficient solution in image denoising. Objective Although a quite number of existing CNN-based image denoising methods perform well on the simplified additive white Gaussian noise (AWGN) model, their performance often degrades severely on the real-world noisy images which are corrupted by more complicated noise. Methods In this paper, we utilized the multi-task learning (MTL) framework to integrate multiple loss functions for collaborative training of CNN. This approach aims to improve the denoising performance of CNNs on real-world images with non-Gaussian noise. Simultaneously, to automatically optimize the weights of individual sub-tasks within the MTL framework, we incorporated a self-learning weight layer into the CNN. Results Extensive experiments demonstrate that our approach effectively enhances the denoising performance of CNN-based image denoising algorithms on real-world images. It reduces excessive image smoothing, improves quantitative metrics, and enhances visual quality in the restored images. Conclusion Our method shows the effectiveness of the improved performance of denoising CNNS for real-world image denoising processing. |
| first_indexed | 2024-04-24T07:15:48Z |
| format | Article |
| id | doaj.art-ffb2d328badb4e6abdef5818e20de9ae |
| institution | Directory Open Access Journal |
| issn | 1110-1903 2536-9512 |
| language | English |
| last_indexed | 2024-04-24T07:15:48Z |
| publishDate | 2024-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Engineering and Applied Science |
| spelling | doaj.art-ffb2d328badb4e6abdef5818e20de9ae2024-04-21T11:20:16ZengSpringerOpenJournal of Engineering and Applied Science1110-19032536-95122024-04-0171111510.1186/s44147-024-00425-7Multi-task learning with self-learning weight for image denoisingQian Xiang0Yong Tang1Xiangyang Zhou2College of Information Science and Engineering, Wuchang Shouyi UniversitySchool of Artificial Intelligence, Hubei Business CollegeCollege of Information Science and Engineering, Wuchang Shouyi UniversityAbstract Background Image denoising technology removes noise from the corrupted image by utilizing different features between image and noise. Convolutional neural network (CNN)-based algorithms have been the concern of the recent progress on diverse image restoration problems and become an efficient solution in image denoising. Objective Although a quite number of existing CNN-based image denoising methods perform well on the simplified additive white Gaussian noise (AWGN) model, their performance often degrades severely on the real-world noisy images which are corrupted by more complicated noise. Methods In this paper, we utilized the multi-task learning (MTL) framework to integrate multiple loss functions for collaborative training of CNN. This approach aims to improve the denoising performance of CNNs on real-world images with non-Gaussian noise. Simultaneously, to automatically optimize the weights of individual sub-tasks within the MTL framework, we incorporated a self-learning weight layer into the CNN. Results Extensive experiments demonstrate that our approach effectively enhances the denoising performance of CNN-based image denoising algorithms on real-world images. It reduces excessive image smoothing, improves quantitative metrics, and enhances visual quality in the restored images. Conclusion Our method shows the effectiveness of the improved performance of denoising CNNS for real-world image denoising processing.https://doi.org/10.1186/s44147-024-00425-7Self-learning weightMulti-objective optimizationNon-Gaussian noise modelImage denoisingMulti-task learningConvolutional neural network |
| spellingShingle | Qian Xiang Yong Tang Xiangyang Zhou Multi-task learning with self-learning weight for image denoising Journal of Engineering and Applied Science Self-learning weight Multi-objective optimization Non-Gaussian noise model Image denoising Multi-task learning Convolutional neural network |
| title | Multi-task learning with self-learning weight for image denoising |
| title_full | Multi-task learning with self-learning weight for image denoising |
| title_fullStr | Multi-task learning with self-learning weight for image denoising |
| title_full_unstemmed | Multi-task learning with self-learning weight for image denoising |
| title_short | Multi-task learning with self-learning weight for image denoising |
| title_sort | multi task learning with self learning weight for image denoising |
| topic | Self-learning weight Multi-objective optimization Non-Gaussian noise model Image denoising Multi-task learning Convolutional neural network |
| url | https://doi.org/10.1186/s44147-024-00425-7 |
| work_keys_str_mv | AT qianxiang multitasklearningwithselflearningweightforimagedenoising AT yongtang multitasklearningwithselflearningweightforimagedenoising AT xiangyangzhou multitasklearningwithselflearningweightforimagedenoising |