Lightweight Single Image Super-Resolution via Efficient Mixture of Transformers and Convolutional Networks
Open Access
Abstract
In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers to provide input-adaptation weighting and global context interaction. We also make use of the advantages of Convolutional Networks to include spatial inductive biases and local connectivity. In the shallow layer, the local spatial information is encoded by Multi-order Local Hierarchical Attention (MLHA). In the deeper layer, we utilize Dynamic Global Sparse Attention (DGSA), which is based on the Multi-stage Token Selection (MTS) strategy to model global context dependencies. Moreover, we also conduct extensive experiments on both natural and satellite datasets, acquired through optical and satellite sensors, respectively, demonstrating that LGUN outperforms existing methods.Keywords
Funding Information
- National Natural Science Foundation of China (62171304, 2024NSFSC1423, 2022CDDZ-09)
- Natural Science Foundation of Sichuan Province (62171304, 2024NSFSC1423, 2022CDDZ-09)
- Cooperation Science and Technology Project of Sichuan University and Dazhou City (62171304, 2024NSFSC1423, 2022CDDZ-09)
This publication has 60 references indexed in Scilit:
- Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation2023
- Exploring more diverse network architectures for single image super-resolutionKnowledge-Based Systems, 2022
- Channel Attention based Network for LiDAR Super-resolution2021
- An efficient Group Skip-Connecting Network for image super-resolutionKnowledge-Based Systems, 2021
- Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network2018
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- CBAM: Convolutional Block Attention Module2018
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Single image super-resolution from transformed self-exemplars2015