Abstract
Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly applying to embedded devices. To reduce the computation resources and maintain performance, we propose a novel Ghost Residual Attention Network (GRAN) for efficient super-resolution. This paper introduces Ghost Residual Attention Block (GRAB) groups to overcome the drawbacks of the standard convolutional operation, i.e., redundancy of the intermediate feature. GRAB consists of the Ghost Module and Channel and Spatial Attention Module (CSAM) to alleviate the generation of redundant features. Specifically, Ghost Module can reveal information underlying intrinsic features by employing linear operations to replace the standard convolutions. Reducing redundant features by the Ghost Module, our model decreases memory and computing resource requirements in the network. The CSAM pays more comprehensive attention to where and what the feature extraction is, which is critical to recovering the image details. Experiments conducted on the benchmark datasets demonstrate the superior performance of our method in both qualitative and quantitative. Compared to the baseline models, we achieve higher performance with lower computational resources, whose parameters and FLOPs have decreased by more than ten times.
Similar content being viewed by others
Data Availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
Code Availability
After the paper is accepted, the code will be open-sourced.
References
Ahn N, Kang B, Sohn KA (2018) Fast, accurate and lightweight super-resolution with cascading residual network
Ai W, Tu X, Cheng S, Xie M (2020) Single image super-resolution via residual neuron attention networks. arXiv:2005.10455
Barzegar S, Sharifi A, Manthouri M (2020) Super-resolution using lightweight detailnet network. Multimed Tools Appl
Bevilacqua M, Roumy A, Guillemot C, Alberi-morel ML (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding
Cai J, Gu S, Timofte R, Zhang L (2019) Ntire 2019 challenge on real image super-resolution: methods and results. In: CVPR
Cai J, Zeng H, Yong H, Cao Z, Zhang L (2019) Toward real-world single image super-resolution: a new benchmark and a new model. In: ICCV
Cao K, Liu Y, Duan L, Xie T (2020) Adaptive residual channel attention network for single image super-resolution. Sci Program
Chen D, He Z, Cao Y, Yang J, Cao Y, Yang MY, Tang S, Zhuang Y (2019) Deep neural network for fast and accurate single image super-resolution via channel-attention-based fusion of orientation-aware features. arXiv:1912.04016
Chen Y, Phonevilay V, Tao J, Chen X, Xia R, Zhang Q, Yang K, Xiong J, Xie J (2021) The face image super-resolution algorithm based on combined representation learning. Multimed Tools Appl
Chen L, Zhang H, Xiao J, Nie L, Shao J, Liu W, Chua T-S (2017) Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR
Chu X, Zhang B, Xu R (2020) Multi-objective reinforced evolution in mobile neural architecture search. In: ECCV
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell
Fan Y, Yu J, Mei Y, Zhang Y, Fu Y, Liu D, Huang TS (2020) Neural sparse representation for image restoration. arXiv:2006.04357
Fu J, Zheng H, Mei T (2017) Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR
Fukuda T, Suzuki M, Kurata G, Thomas S, Cui J, Ramabhadran B (2017) Efficient knowledge distillation from an ensemble of teachers. In: Interspeech
Guo Y, Zhang C, Zhang C, Chen Y (2018) Sparse dnns with improved adversarial robustness neurIPS
Han S, Mao H, Dally WJ (2015) Deep compression: compressing deep neural networks with pruning trained quantization and huffman coding
Han K, Wang Y, Tian Q, Guo J, Xu C (2020) Ghostnet: more features from cheap operations. In: CVPR
Haris M, Shakhnarovich G, Ukita N (2019) Deep back-projection networks for single image super-resolution. arXiv:1904.05677
Heo B, Lee M, Yun S, Choi JY (2019) Knowledge distillation with adversarial samples supporting decision boundary. In: AAAI
Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531
Hu Y, Li J, Huang Y, Gao X (2019) Channel-wise and spatial feature modulation network for single image super-resolution. IEEE Trans Circuits Syst Vid Technol
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: CVPR
Hu S, Wang G, Wang Y, Chen C, Pan Z (2020) Accurate image super-resolution using dense connections and dimension reduction network. Multimed Tools Appl
Huang J-B, Singh A, Ahuja N (2015) Single image super-resolution from transformed self-exemplars. In: CVPR
Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. arXiv:1506.02025
Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: CVPR
Li X, Chen Z (2021) Single image super-resolution reconstruction based on fusion of internal and external features. Multimed Tools Appl
Li J, Fang F, Mei K, Zhang G (2018) Multi-scale residual network for image super-resolution: 15th european conference, munich, germany, 8-14 Sept 2018, proceedings, part viii. In: ECCV
Li R, He X, Zhu Y, Li X, Sun J, Zhang Y (2020) Enhancing self-supervised monocular depth estimation via incorporating robust constraints. In: Proceedings of the 28th ACM international conference on multimedia
Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. arXiv:1608.08710
Li R, Sun J, Gong D, Zhu Y, Li H, Zhang Y (2019) Arsac: efficient model estimation via adaptively ranked sample consensus. Neurocomputing
Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution
Liu M, Zhang Z, Hou L, Zuo W, Zhang L (2020) Deep adaptive inference networks for single image super-resolution. arXiv:2004.03915
Lu X, Yuan Y, Yan P (2014) Alternatively constrained dictionary learning for image superresolution. IEEE Trans Cybern
Lyn J (2020) Multi-level feature fusion mechanism for single image super-resolution. arXiv:2002.05962
Ma H, Chu X, Zhang B, Wan S (2019) A matrix-in-matrix neural network for image super resolution. arXiv:1903.07949
Mao Q, Li R, Zhu Y, Sun J, Zhang Y (2023) Enhancing 3d-2d representations for convolution occupancy networks. Pattern Recognit
Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV
Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K (2017) Sketch-based manga retrieval using manga109 dataset. Multimed Tools Appl
Muqeet A, Iqbal MTB, Bae S-H (2019) Hybrid residual attention network for single image super resolution. arXiv:1907.05514
Niu A, Zhang K, Pham TX, Sun J, Zhu Y, Kweon IS, Zhang Y (2023) Cdpmsr: conditional diffusion probabilistic models for single image super-resolution. arXiv:2302.12831
Niu A, Zhu Y, Zhang C, Sun J, Wang P, Kweon IS, Zhang Y (2022) Ms2net: multi-scale and multi-stage feature fusion for blurred image super-resolution. IEEE Transactions on Circuits and Systems for Video Technology
Niu A, Zhang K, Pham TX, Sun J, Zhu Y, Kweon IS, Zhang Y (2023) Cdpmsr: conditional diffusion probabilistic models for single image super-resolution. arXiv:2202.05488
Peng Y (2020) Super-resolution reconstruction using multiconnection deep residual network combined an improved loss function for single-frame image. Multimed Tools Appl
Peng H, Wu J, Chen S, Huang J (2019) Collaborative channel pruning for deep networks. In: ICML
Rajput SS, Arya K (2020) A robust face super-resolution algorithm and its application in low-resolution face recognition system. Multimed Tools Appl
Salvador J, Perez-Pellitero E (2016) Naive bayes super-resolution forest. In: IEEE international conference on computer vision
Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. In: CVPR
Shamsolmoali P, Zareapoor M, Jain DK, Jain VK, Yang J (2019) Deep convolution network for surveillance records super-resolution. Multimed Tool Appl
Singh A, Singh J (2020) Survey on single image based super-resolution—implementation challenges and solutions. Multimed Tools Appl
Song Z, Zhao X, Jiang H (2021) Gradual deep residual network for super-resolution. Multimed Tools Appl
Tai YW, Liu S, Brown MS, Lin S (2010) Super resolution using edge prior and single image detail synthesis. In: CVPR
Timofte R, Agustsson E, Van Gool L, Yang M-H, Zhang L (2017) Ntire 2017 challenge on single image super-resolution: methods and results. In: CVPR workshops
Timofte R, De V, Gool LV (2014) Anchored neighborhood regression for fast example-based super-resolution. In: ICCV
Wang Z, Chen J, Hoi SCH (2020) Deep learning for image super-resolution: a survey. IEEE Trans Pattern Anal Mach Intell
Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Loy CC, Qiao Y, Tang X (2018) Esrgan: enhanced super-resolution generative adversarial networks
Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: convolutional block attention module
Woo S, Park J, Lee J-Y, So Kweon I (2018) Cbam: convolutional block attention module. In: ECCV
Yang H, Tong J, Dou Q, Xiao L, Jeon G, Yang X (2021) Wide receptive field networks for single image super-resolution. Multimed Tools Appl
Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. TIP
Yu J, Gao X, Tao D, Li X, Zhang K (2014) A unified learning framework for single image super-resolution. TNNLS
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse-representations. In: International conference on curves and surfaces
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y (2018) Image super-resolution using very deep residual channel attention networks. In: ECCV
Zhao H, Jia J, Koltun V (2020) Exploring self-attention for image recognition. In: CVPR
Zhu X, Cheng D, Zhang Z, Lin S, Dai J (2020) An empirical study of spatial attention mechanisms in deep networks. In: ICCV
Funding
This work was funded in part by the Project of the National Natural Science Foundation of China under Grant 61901384 and 61871328, the Natural Science Basic Research Program of Shaanxi under Grant 2021JCW-03, as well as the Joint Funds of the National Natural Science Foundation of China under Grant U19B2037.
Author information
Authors and Affiliations
Contributions
Conceptualization, A.N, and Q.Y.; methodology, A.N.; software, A.N, P.W.; validation, A.N., P.W.; formal analysis, A.N.; investigation, P.W.; resources, Y.Z.; data curation, J.S.; writing—original draft preparation, A.N.; writing—review and editing, A.N., P.W., Y.Z, S.J.; visualization, P.W.; supervision, S.J.; project administration, A.N., Y.Z. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Niu, A., Wang, P., Zhu, Y. et al. GRAN: ghost residual attention network for single image super resolution. Multimed Tools Appl 83, 28505–28522 (2024). https://doi.org/10.1007/s11042-023-15088-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15088-4