| Title: |
A Multi-Attention Feature Distillation Neural Network for Lightweight Single Image Super-Resolution |
| Authors: |
Zhang, Yongfei; Lin, Xinying; Yang, Hong; He, Jie; Qing, Linbo; He, Xiaohai; Li, Yi; Chen, Honggang |
| Contributors: |
Khosravi, Mohammad R.; National Natural Science Foundation of China; Sichuan Province Science and Technology Support Program; Guangxi Key Laboratory of Multi-Source Information Mining and Security; Ministry of Education of the People’s Republic of China; Research Fund of Guangxi Key Laboratory of Machine Vision and Intelligent Control; Open Foundation of Yunnan Key Laboratory of Software Engineering; Fundamental Research Funds for the Central Universities |
| Source: |
International Journal of Intelligent Systems ; volume 2024, page 1-14 ; ISSN 1098-111X 0884-8173 |
| Publisher Information: |
Wiley |
| Publication Year: |
2024 |
| Collection: |
Wiley Online Library (Open Access Articles via Crossref) |
| Description: |
In recent years, remarkable performance improvements have been produced by deep convolutional neural networks (CNN) for single image super-resolution (SISR). Nevertheless, a high proportion of CNN-based SISR models are with quite a few network parameters and high computational complexity for deep or wide architectures. How to more fully utilize deep features to make a balance between model complexity and reconstruction performance is one of the main challenges in this field. To address this problem, on the basis of the well-known information multi-distillation model, a multi-attention feature distillation network termed as MAFDN is developed for lightweight and accurate SISR. Specifically, an effective multi-attention feature distillation block (MAFDB) is designed and used as the basic feature extraction unit in MAFDN. With the help of multi-attention layers including pixel attention, spatial attention, and channel attention, MAFDB uses multiple information distillation branches to learn more discriminative and representative features. Furthermore, MAFDB introduces the depthwise over-parameterized convolutional layer (DO-Conv)-based residual block (OPCRB) to enhance its ability without incurring any parameter and computation increase in the inference stage. The results on commonly used datasets demonstrate that our MAFDN outperforms existing representative lightweight SISR models when taking both reconstruction performance and model complexity into consideration. For example, for 4 SR on Set5, MAFDN (597K/33.79G) obtains 0.21 dB/0.0037 and 0.10 dB/0.0015 PSNR/SSIM gains over the attention-based SR model AFAN (692K/50.90G) and the feature distillation-based SR model DDistill-SR (675K/32.83G), respectively. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| DOI: |
10.1155/2024/3255233 |
| Availability: |
https://doi.org/10.1155/2024/3255233; http://downloads.hindawi.com/journals/ijis/2024/3255233.pdf; http://downloads.hindawi.com/journals/ijis/2024/3255233.xml |
| Rights: |
https://creativecommons.org/licenses/by/4.0/ |
| Accession Number: |
edsbas.EE20D025 |
| Database: |
BASE |