A Multi-Attention Feature Distillation Neural Network for Lightweight Single Image Super-Resolution
Open Access
- 15 February 2024
- journal article
- research article
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2024, 1-14
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Sichuan Provincial Science and Technology Support Program (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Guangxi Key Laboratory of Multi-Source Information Mining and Security (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Ministry of Education of the People’s Republic of China (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Research Fund of Guangxi Key Laboratory of Machine Vision and Intelligent Control (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Open Foundation of Yunnan Key Laboratory of Software Engineering (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
- Fundamental Research Funds for the Central Universities (62001316, 61961036, 24QYCX0399, MIMS22-14, TJUT-CVS20220001, 2022B05, 2023SE206, SCU2023D062, 2021CDDZ-08-SCU, 2022CDSN-15-SCU)
This publication has 83 references indexed in Scilit:
- Hierarchical dense recursive network for image super-resolutionPattern Recognition, 2020
- Channel Splitting Network for Single MR Image Super-ResolutionIEEE Transactions on Image Processing, 2019
- Channel-Wise and Spatial Feature Modulation Network for Single Image Super-ResolutionIEEE Transactions on Circuits and Systems for Video Technology, 2019
- Single image super-resolution using collaborative representation and non-local self-similaritySignal Processing, 2018
- Single Image Super-Resolution via Adaptive Transform-Based Nonlocal Self-Similarity Modeling and Learning-Based Gradient RegularizationIEEE Transactions on Multimedia, 2017
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Sparse Representation Based Image Interpolation With Nonlocal Autoregressive ModelingIEEE Transactions on Image Processing, 2013
- Nonlocally Centralized Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2012
- Single Image Super-Resolution With Non-Local Means and Steering Kernel RegressionIEEE Transactions on Image Processing, 2012
- Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision EstimationIEEE Transactions on Image Processing, 2008