Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection
In single image super-resolution problems, the recent feed forward deep learning architectures use residual connections in order to preserve local features and carry them through the next layer. In a simple residual skip connection, all the features of the earlier layer are concatenated with the fea...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8705224/ |
| _version_ | 1818412314432372736 |
|---|---|
| author | Ruaa A. Al-falluji Aliaa A. A Youssif Shawkat K. Guirguis |
| author_facet | Ruaa A. Al-falluji Aliaa A. A Youssif Shawkat K. Guirguis |
| author_sort | Ruaa A. Al-falluji |
| collection | DOAJ |
| description | In single image super-resolution problems, the recent feed forward deep learning architectures use residual connections in order to preserve local features and carry them through the next layer. In a simple residual skip connection, all the features of the earlier layer are concatenated with the features of the current layer. A simple concatenation of the features does not exploit the fact that some features may be more useful than other features and vice versa. To overcome this limitation, we propose an extended architecture (baby neural network) which will have input as the features learned from the previous layer and output a multiplication factor. This multiplication factor will give importance to the given feature and thus help in training the current layer's features more accurately. The proposed model clearly outperforms the existing works. |
| first_indexed | 2024-12-14T10:45:20Z |
| format | Article |
| id | doaj.art-65d84959438d4ac5ba30d6614b522d9d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:45:20Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-65d84959438d4ac5ba30d6614b522d9d2022-12-21T23:05:27ZengIEEEIEEE Access2169-35362019-01-017586765868410.1109/ACCESS.2019.29147398705224Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip ConnectionRuaa A. Al-falluji0https://orcid.org/0000-0002-1425-6213Aliaa A. A Youssif1Shawkat K. Guirguis2Babylon University, Babylon, IraqArab Academy for Science, Technology & Maritime Transport (AASTMT), Cairo, EgyptInstitute of Graduate Studies and Research (IGSR), Alexandria University, Alexandria, EgyptIn single image super-resolution problems, the recent feed forward deep learning architectures use residual connections in order to preserve local features and carry them through the next layer. In a simple residual skip connection, all the features of the earlier layer are concatenated with the features of the current layer. A simple concatenation of the features does not exploit the fact that some features may be more useful than other features and vice versa. To overcome this limitation, we propose an extended architecture (baby neural network) which will have input as the features learned from the previous layer and output a multiplication factor. This multiplication factor will give importance to the given feature and thus help in training the current layer's features more accurately. The proposed model clearly outperforms the existing works.https://ieeexplore.ieee.org/document/8705224/Super resolutionimage enhancementimage reconstructionresidual skip connectionconvolutional neural networks |
| spellingShingle | Ruaa A. Al-falluji Aliaa A. A Youssif Shawkat K. Guirguis Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection IEEE Access Super resolution image enhancement image reconstruction residual skip connection convolutional neural networks |
| title | Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection |
| title_full | Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection |
| title_fullStr | Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection |
| title_full_unstemmed | Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection |
| title_short | Single Image Super Resolution Model Using Learnable Weight Factor in Residual Skip Connection |
| title_sort | single image super resolution model using learnable weight factor in residual skip connection |
| topic | Super resolution image enhancement image reconstruction residual skip connection convolutional neural networks |
| url | https://ieeexplore.ieee.org/document/8705224/ |
| work_keys_str_mv | AT ruaaaalfalluji singleimagesuperresolutionmodelusinglearnableweightfactorinresidualskipconnection AT aliaaaayoussif singleimagesuperresolutionmodelusinglearnableweightfactorinresidualskipconnection AT shawkatkguirguis singleimagesuperresolutionmodelusinglearnableweightfactorinresidualskipconnection |