Convolutional Neural Networks Using Skip Connections with Layer Groups for Super-Resolution Image Reconstruction Based on Deep Learning
Source abstract
Abstract
In this paper, we propose a deep learning method with convolutional neural networks (CNNs) using skip connections with layer groups for super-resolution image reconstruction. In the proposed method, entire CNN layers for residual data processing are divided into several layer groups, and skip connections with different multiplication factors are applied from input data to these layer groups. With the proposed method, the processed data in hidden layer units tend to be distributed in a wider range. Consequently, the feature information from input data is transmitted to the output more robustly. Experimental results show that the proposed method yields a higher peak signal-to-noise ratio and better subjective quality than existing methods for super-resolution image reconstruction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image Processing Techniques and Applications · Advanced Vision and Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Intelligent Image Processing Laboratory, Konkuk University, Seoul 05029, Korea
Funding
Konkuk University
References (12)
Show source-provided references
1. Image super-resolution using deep convolutional networks10.1109/TPAMI.2015.2439281 ↗
2. Kim, J., Lee, J., and Lee, K. (2016, January 27–30). Accurate image super-resolution using very deep convolutional networks. Proceedings of the International Conference Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.182 ↗
3. Jiang, Q., Tan, D.C., Li, Y., Ji, S., Cai, C., and Zheng, Q. (2019). Object detection and classification of metal polishing shaft surface defects based on convolutional neural network deep learning. Appl. Sci., 10.10.3390/app10010087 ↗
4. Dang, L.M., Min, K., Lee, S., Han, D., and Moon, H. (2020). Tampered and computer-generated face images identification based on deep learning. Appl. Sci., 10.10.3390/app10020505 ↗
5. The vanishing gradient problem during learning recurrent neural nets and problem solutions10.1142/S0218488598000094 ↗
6. Batch normalization: Accelerating deep network training by reducing internal covariate shift
7. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the International Conference Computer Vision Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
8. Huang, Z., and Wang, N. (2018). Data-driven sparse structure selection for deep neural networks. arXiv.10.1007/978-3-030-01270-0_19 ↗
9. Image super-resolution via sparse representation10.1109/TIP.2010.2050625 ↗
10. Martin, D., Fowlkes, C., Tal, D., and Malik, J. (2001, January 7–14). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings of the Eighth IEEE International Conference on Computer Vision, Vancouver, BC, Canada.
11. Timofte, R., Smet, V.D., and Gool, L.V. (2014). A+: Adjusted anchored neighborhood regression for fast super-resolution. Asian Conference on Computer Vision, Springer.10.1109/ICCV.2013.241 ↗
12. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for stochastic optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.