Mir Sazzat Hossain
- Research Assistant, CCDS
Bachelors
Independent University, Bangladesh
Research Interests
Machine Learning, Computer Vision
Conference Paper2024Cited by 1
Lightweight Recurrent Neural Network for Image Super-resolution
Mir Sazzat Hossain, AKM Mahbubur Rahman, Md. Ashraful Amin, Amin Ahsan Ali
IEEE Int'l Conf on Image Processing
IEEE, pp. 1567-1573
Abstract
In recent years, significant progress has been made in image super-resolution through the use of large-scale models. However, the efficacy of these models comes at the cost of their substantial size, posing challenges and limitations when deploying them on resource-constrained devices. Despite their remarkable performance, the feasibility of employing such models on low-end devices has remained a contentious topic. In light of this, our research introduces a lightweight approach to image super-resolution, leveraging a simple recurrent neural network architecture consisting of a recurrent convolution block. Our proposed model uses less than 75k parameters, which is 10 times fewer than the state-of-the-art transformer-based super-resolution model. Despite its small size, the proposed model performs well in image super-resolution tasks both visually and quantitatively. Our work presents a promising direction for addressing the difficulty of deploying efficient super-resolution models on resource-limited devices.
Keywords
Computer scienceArtificial intelligenceArtificial neural networkImage (mathematics)Computer visionResolution (logic)Image resolution
CCDS Authors
AKM Mahbubur Rahman, PhD
- Director, DS & IPT Wings
Associate Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
Prof. M Ashraful Amin, PhD
- Founder Director, CCDS
- Director, AI/ML, HCI & DS Wings
Professor
+1 more affiliationDepartment of Information Sciences and Technology
George Mason University, USA
Research Interests
Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics
Amin Ahsan Ali, PhD
- Director, AI/ML Wing
Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
Research Interests
Artificial Intelligence, Machine Learning
References
- 1.D. Martin, C. Fowlkes, D. Tal, J. Malik. (2002). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. , 2, 416–423[10.1109/iccv.2001.937655]
- 2.Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. (2014). Learning a Deep Convolutional Network for Image Super-Resolution. Lecture notes in computer science, 184–199[10.1007/978-3-319-10593-2_13]
- 3.P Arbeláez, M Maire, C Fowlkes, J Malik. (2010). Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898–916[10.1109/tpami.2010.161]
- 4.Jianchao Yang, John Wright, Thomas S Huang, Yi Ma. (2010). Image Super-Resolution Via Sparse Representation. IEEE Transactions on Image Processing, 19(11), 2861–2873[10.1109/tip.2010.2050625]
- 5.Eirikur Agustsson, Radu Timofte. (2017). NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study. , 1122–1131[10.1109/cvprw.2017.150]
- 6.Jia-Bin Huang, Abhishek Singh, Narendra Ahuja. (2015). Single image super-resolution from transformed self-exemplars. , 5197–5206[10.1109/cvpr.2015.7299156]
- 7.Roman Zeyde, Michael Elad, Matan Protter. (2012). On Single Image Scale-Up Using Sparse-Representations. Lecture notes in computer science, 711–730[10.1007/978-3-642-27413-8_47]
- 8.Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee. (2016). Deeply-Recursive Convolutional Network for Image Super-Resolution. , 1637–1645[10.1109/cvpr.2016.181]
- 9.Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-line Alberi Morel. (2012). Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. , 135.1–135.10[10.5244/c.26.135]
- 10.Ying Tai, Jian Yang, Xiaoming Liu. (2017). Image Super-Resolution via Deep Recursive Residual Network. , 2790–2798[10.1109/cvpr.2017.298]
- 11.Ying Tai, Jian Yang, Xiaoming Liu, Chunyan Xu. (2017). MemNet: A Persistent Memory Network for Image Restoration. , 4549–4557[10.1109/iccv.2017.486]
- 12.Zheng Hui, Xinbo Gao, Yunchu Yang, Xiumei Wang. (2019). Lightweight Image Super-Resolution with Information Multi-distillation Network. , 2024–2032[10.1145/3343031.3351084]
- 13.Jie Liu, Jie Tang, Gangshan Wu. (2020). Residual Feature Distillation Network for Lightweight Image Super-Resolution. Lecture notes in computer science, 41–55[10.1007/978-3-030-67070-2_2]
- 14.Xiaotong Luo, Yuan Xie, Yulun Zhang, Yanyun Qu, Cuihua Li, Yun Fu. (2020). LatticeNet: Towards Lightweight Image Super-Resolution with Lattice Block. Lecture notes in computer science, 272–289[10.1007/978-3-030-58542-6_17]
- 15.Haram Choi, Jeongmin Lee, Jihoon Yang. (2023). N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution. , 2071–2081[10.1109/cvpr52729.2023.00206]
- 16.Jinsheng Fang, Hanjiang Lin, Xinyu Chen, Kun Zeng. (2022). A Hybrid Network of CNN and Transformer for Lightweight Image Super-Resolution. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1102–1111[10.1109/cvprw56347.2022.00119]
- 17.Zongcai Du, Ding Liu, Jie Liu, Jie Tang, Gangshan Wu, Lean Fu. (2022). Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 852–861[10.1109/cvprw56347.2022.00101]
- 18.Cheeun Hong, Heewon Kim, Sungyong Baik, Junghun Oh, Kyoung Mu Lee. (2022). DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks. 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 913–922[10.1109/wacv51458.2022.00099]
Cited By
- 1.Sunwoo Cho, Yejin Jung, Nam Ik Cho, Jae Woong Soh. (2025). Dataset Distillation for Super-Resolution Without Class Labels and Pre-Trained Models. IEEE Signal Processing Letters, 32, 3700–3704[10.1109/lsp.2025.3611694]