Abstract
Deep learning methods have been widely applied in image compressed sensing (CS) recently, which achieve a significant improvement to traditional reconstruction algorithms in both running speed and reconstruction quality. However, it is a time-consuming procedure even for an expert to efficiently design a high-performance network for image CS because of various combination of different kernel size and filter number in each layer. In this paper, a novel image CS framework named NAS-CSNet is presented by leveraging virtues from neural architecture search (NAS) technique. The NAS-CSNet includes a sampling network, an initial reconstruction network and a NAS-based reconstruction network, which are optimized jointly. In particular, the reconstruction network is automatically designed by searching from the search space without trials and errors by experts. Extensive experimental results demonstrate that our proposed method achieves the competitive performance compared with the state-of-the-art deep learning methods and numerically promotes the reconstruction accuracy considerably, showing the effectiveness of the proposed NAS-CSNet and the promise to further use of NAS in the CS field.
This paper is supported by National Key Research and Development Program of China under grant No. 2018YFB1003500, No. 2018YFB0204400 and No. 2017YFB1401202.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)
Candès, E.J., Tao, T.: Near-optimal signal recovery from random projections: universal encoding strategies? IEEE Trans. Inf. Theory 12(52), 5406–5425 (2006)
Candès, E.J.: The restricted isometry property and its implications for compressed sensing. Comptes Rendus Mathematique 9(346), 589–592 (2008)
Needell, D., Tropp, J.: CoSaMP: iterative signal recovery from incomplete and inaccurate samples. Appl. Comput. Harmonic Anal. 3(26), 301–321 (2009)
Figueiredo, M.A., Nowak, R.D., Wright, S.J.: Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems. IEEE J. Sel. Topics Signal Process. 1(4), 586–597 (2007)
Ji, S., Xue, Y., Carin, L.: Bayesian compressive sensing. IEEE Trans. Signal Process. 6(56), 2346–2356 (2008)
Wu, Y., Rosca, M., Lillicrap, T.: Deep compressed sensing. In: Proceedings of the 36th International Conference on Machine Learning, pp. 6850–6860 (2019)
Lyu, C., Liu, Z., Yu, L.: Block-sparsity recovery via recurrent neural network. Signal Process. 154, 129–135 (2019)
Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., Ashok, A.: ReconNet: non-iterative reconstruction of images from compressively sensed measurements. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 449–458 (2016)
Shi, W., Jiang, F., Zhang, S., Zhao, D.: Deep networks for compressed image sensing. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 877–882. IEEE (2017)
Xu, K., Zhang, Z., Ren, F.: LAPRAN: a scalable laplacian pyramid reconstructive adversarial network for flexible compressive sensing reconstruction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 491–507. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_30
Shi, W., Jiang, F., Liu, S., Zhao, D.: Image compressed sensing using convolutional neural network. IEEE Trans. Image Process. 29, 375–388 (2019)
Shi, W., Jiang, F., Liu, S., Zhao, D.: Scalable convolutional neural network for image compressed sensing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12290–12299 (2019)
Ghiasi, G., Lin, T.-Y., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019)
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4780–4789 (2019)
Luong, M.T., Dohan, D., Yu, A.W., Le, Q.V., Zoph, B., Vasudevan, V.: Exploring neural architecture search for language tasks. In: 6th International Conference on Learning Representations, ICLR, May 2018
Cai, H., Chen, T., Zhang, W., Yu, Y., Wang, J.: Efficient architecture search by network transformation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2787–2794 (2018)
Elsken, T., Metzen, J.H., Hutter, F.: Efficient multi-objective neural architecture search via Lamarckian evolution. In: 7th International Conference on Learning Representations, ICLR, May 2019
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)
Liu, H., Karen Simonyan, C.F., Vinyals, O., Kavukcuoglu, K.: Hierarchical representations for efficient architecture search. In: 6th International Conference on Learning Representations, ICLR, May 2018
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: 5th International Conference on Learning Representations, ICLR, April 2017
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: 7th International Conference on Learning Representations, ICLR, May 2019
Real, E., et al.: Large-scale evolution of image classifiers. In: Proceedings of the 34th International Conference on Machine Learning, ICML, August 2017, pp. 2902–2911
Lu, Z., et al.: NSGA-Net: neural architecture search using multi-objective genetic algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 419–427. ACM (2019)
Yang, X.-S., Deb, S.: Cuckoo search via Lévy flights. In: 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC), pp. 210–214. IEEE (2009)
Wang, F., He, X., Wang, Y., Yang, S.: Markov model and convergence analysis based on cuckoo search algorithm. Comput. Eng. 38(11), 180–185 (2012)
Mantegna, R.N.: Fast, accurate algorithm for numerical simulation of Lévy stable stochastic processes. Phys. Rev. E 49(5), 4677–4683 (1994)
Mousavi, A., Patel, A.B., Baraniuk, R.G.: A deep learning approach to structured signal recovery. In: 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 1336–1343. IEEE (2015)
Zhang, J., Ghanem, B.: ISTA-Net: interpretable optimization-inspired deep network for image compressive sensing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1828–1837 (2018)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, N., Wang, J., Qu, X., Xiao, J. (2021). Image Compressed Sensing Using Neural Architecture Search. In: Mei, H., et al. Big Data. BigData 2020. Communications in Computer and Information Science, vol 1320. Springer, Singapore. https://doi.org/10.1007/978-981-16-0705-9_2
Download citation
DOI: https://doi.org/10.1007/978-981-16-0705-9_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0704-2
Online ISBN: 978-981-16-0705-9
eBook Packages: Computer ScienceComputer Science (R0)
