Advertisement

Single Image Super-Resolution Using Lightweight CNN with Maxout Units

  • Jae-Seok Choi
  • Munchurl KimEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11366)

Abstract

Rectified linear units (ReLU) are well-known to obtain higher performance for deep-learning-based applications. However, networks with ReLU tend to perform poorly when the number of parameters is constrained. To overcome, we propose a novel network utilizing maxout units (MU), and show its effectiveness on super-resolution (SR). In this paper, we first reveal that MU can make the filter sizes halved in restoration problems thus leading to compaction of the network. To the best of our knowledge, we are the first to incorporate MU into SR applications and show promising results. In MU, feature maps from a previous convolutional layer are divided into two parts along channels, which are compared element-wise and only their max values are passed to a next layer. Along with interesting properties of MU to be analyzed, we further investigate other variants of MU. Our MU-based SR method reconstructs images with comparable quality compared to previous SR methods, even with smaller parameters.

Keywords

Super-resolution (SR) Convolutional neural network (CNN) Maxout unit (MU) Lightweight 

Supplementary material

484523_1_En_30_MOESM1_ESM.pdf (118 kb)
Supplementary material 1 (pdf 118 KB)

References

  1. 1.
    Abadi, M., Barham, P., Chen, J., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)Google Scholar
  2. 2.
    Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
  3. 3.
    Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding (2012)Google Scholar
  4. 4.
    Cai, B., Xu, X., Jia, K., Qing, C., Tao, D.: DehazeNet: an end-to-end system for single image haze removal. IEEE Trans. Image Proc. 25(11), 5187–5198 (2016)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Chang, J.R., Chen, Y.S.: Batch-normalized maxout network in network. arXiv preprint arXiv:1511.02583 (2015)
  6. 6.
    Choi, J.S., Kim, M.: Super-interpolation with edge-orientation-based mapping kernels for low complex 2\(\times \) upscaling. IEEE Trans. Image Proc. 25(1), 469–483 (2016)Google Scholar
  7. 7.
    Choi, J.S., Kim, M.: A deep convolutional neural network with selection units for super-resolution. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition Workshops, pp. 1150–1156 (2017)Google Scholar
  8. 8.
    Choi, J.S., Kim, M.: Single image super-resolution using global regression based on multiple local linear mappings. IEEE Trans. Image Proc. 26(3), 1300–1314 (2017)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUS). arXiv preprint arXiv:1511.07289 (2015)
  10. 10.
    Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10593-2_13CrossRefGoogle Scholar
  11. 11.
    Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)CrossRefGoogle Scholar
  12. 12.
    Freedman, G., Fattal, R.: Image and video upscaling from local self-examples. ACM Trans. Graph. 30(2), 12 (2011)CrossRefGoogle Scholar
  13. 13.
    Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super-resolution. IEEE Comput. Graph. Appl. 22(2), 56–65 (2002)CrossRefGoogle Scholar
  14. 14.
    Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: IEEE International Conference Computer Vision, pp. 349–356 (2009)Google Scholar
  15. 15.
    Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv preprint arXiv:1302.4389 (2013)
  16. 16.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference Computer Vision, pp. 1026–1034 (2015)Google Scholar
  17. 17.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_38CrossRefGoogle Scholar
  18. 18.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)Google Scholar
  19. 19.
    Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference Multimedia, pp. 675–678 (2014)Google Scholar
  20. 20.
    Jianchao, Y., Wright, J., Huang, T., Ma, Y.: Image super-resolution as sparse representation of raw image patches. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition, pp. 1–8 (2008)Google Scholar
  21. 21.
    Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition, pp. 1646–1654 (2016)Google Scholar
  22. 22.
    Kim, K.I., Kwon, Y.: Single-image super-resolution using sparse regression and natural image prior. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1127–1133 (2010)CrossRefGoogle Scholar
  23. 23.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  24. 24.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  25. 25.
    Ledig, C., Theis, L., Huszár, F., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, vol. 2, p. 4 (2017)Google Scholar
  26. 26.
    Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition Workshops, vol. 1, p. 3 (2017)Google Scholar
  27. 27.
    Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the International Conference on Machine Learning, vol. 30, p. 3 (2013)Google Scholar
  28. 28.
    Martin, D., Fowlkes, C., et al.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 2, pp. 416–423 (2001)Google Scholar
  29. 29.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the International Conference on Machine Learning, pp. 807–814 (2010)Google Scholar
  30. 30.
    Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  31. 31.
    Shi, W., Caballero, J., Huszár, F., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, pp. 1874–1883 (2016)Google Scholar
  32. 32.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  33. 33.
    Swietojanski, P., Li, J., Huang, J.T.: Investigation of maxout networks for speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7649–7653 (2014)Google Scholar
  34. 34.
    Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition Workshops, vol. 1 (2017)Google Scholar
  35. 35.
    Timofte, R., Agustsson, E., Van Gool, L., et al.: Ntire 2017 challenge on single image super-resolution: methods and results. In: Proceedings of the IEEE Conference on Computer Vision Pattern Recognition Workshops, pp. 1110–1121 (2017)Google Scholar
  36. 36.
    Timofte, R., De Smet, V., Van Gool, L.: A+: adjusted anchored neighborhood regression for fast super-resolution. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 111–126. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16817-3_8CrossRefGoogle Scholar
  37. 37.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Proc. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  38. 38.
    Yang, C.-Y., Huang, J.-B., Yang, M.-H.: Exploiting self-similarities for single frame super-resolution. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6494, pp. 497–510. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-19318-7_39CrossRefGoogle Scholar
  39. 39.
    Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Proc. 19(11), 2861–2873 (2010)MathSciNetCrossRefGoogle Scholar
  40. 40.
    Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J.-D., et al. (eds.) Curves and Surfaces 2010. LNCS, vol. 6920, pp. 711–730. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-27413-8_47CrossRefGoogle Scholar
  41. 41.
    Zhang, K., Gao, X., Tao, D., Li, X.: Single image super-resolution with non-local means and steering kernel regression. IEEE Trans. Image Proc. 21(11), 4544–4556 (2012)MathSciNetCrossRefGoogle Scholar
  42. 42.
    Zhang, K., Tao, D., Gao, X., Li, X., Xiong, Z.: Learning multiple linear mappings for efficient single image super-resolution. IEEE Trans. Image Proc. 24(3), 846–861 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of EEKorea Advanced Institute of Science and TechnologyDaejeonKorea

Personalised recommendations