Abstract
In this paper, we introduce variational networks (VNs) for image reconstruction. VNs are fully learned models based on the framework of incremental proximal gradient methods. They provide a natural transition between classical variational methods and state-of-the-art residual neural networks. Due to their incremental nature, VNs are very efficient, but only approximately minimize the underlying variational model. Surprisingly, in our numerical experiments on image reconstruction problems it turns out that giving up exact minimization leads to a consistent performance increase, in particular in the case of convex models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alexandre, B.: Sharesnet: reducing residual network parameter number by sharing weights. arXiv e-prints 1702.08782 (2017)
Bertalmio, M., Sapiro, G., Randall, G.: Morphing active contours. TPAMI 22(7), 733–737 (2000)
Bertsekas, D.P.: Incremental proximal methods for large scale convex optimization. Math. Program. 129(2), 163 (2011). doi:10.1007/s10107-011-0472-0
Black, M.J., Anandan, P.: The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63(1), 75–104 (1996)
Blake, A., Zisserman, A.: Visual Reconstruction. MIT Press, Cambridge (1987)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)
Bredies, K., Kunisch, K., Pock, T.: Total generalized variation. SIIMS 3(3), 492–526 (2010)
Chambolle, A., Lions, P.L.: Image recovery via total variation minimization and related problems. Numer. Math. 76(2), 167–188 (1997)
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)
Chen, Y., Ranftl, R., Pock, T.: Insights into analysis operator learning: from patch-based sparse models to higher order MRFs. IEEE Trans. Image Process. 23(3), 1060–1072 (2014)
Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: CVPR (2015)
Dabov, K., Foi, A., Katkovnik, V.: Image denoising by sparse 3D transformation-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 1–16 (2007)
Domke, J.: Generic methods for optimization-based modeling. In: AISTATS, pp. 318–326 (2012)
Freedman, D., Zhang, T.: Active contours for tracking distributions. IEEE Trans. Image Process. 13(4), 518–526 (2004)
Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: ICML (2010)
Hammernik, K., Knoll, F., Sodickson, D., Pock, T.: Learning a variational model for compressed sensing MRI reconstruction. In: ISMRM (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2016)
Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)
Klatzer, T., Hammernik, K., Knöbelreiter, P., Pock, T.: Learning joint demosaicing and denoising based on sequential energy minimization. In: ICCP (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)
Kunisch, K., Pock, T.: A bilevel optimization approach for parameter learning in variational models. SIIMS 6, 938–983 (2013)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Lee, A.B., Pedersen, K.S., Mumford, D.: The nonlinear statistics of high-contrast patches in natural images. IJCV 54(1–3), 83–103 (2003)
Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR (2009)
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). doi:10.1007/978-3-319-10602-1_48
Mao, X.J., Shen, C., Yang, Y.B.: Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv e-prints 1606.08921 (2016)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV (2001)
Masoud, A., Saeid, N.: Multi-residual networks. arXiv e-prints 1609.05672 (2016)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42(5), 577–685 (1989)
Nedić, A., Bertsekas, D.: Convergence rate of incremental subgradient algorithms. In: Uryasev, S., Pardalos, P.M. (eds.) Stochastic Optimization: Algorithms and Applications. Applied Optimization, vol. 54, pp. 223–264. Springer, Boston (2001)
Roth, S., Black, M.J.: Fields of experts. IJCV 82, 205–229 (2009)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D: Nonlinear Phenom. 60(1–4), 259–268 (1992)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Schelten, K., Nowozin, S., Jancsary, J., Rother, C., Roth, S.: Interleaved regression tree field cascades for blind image deconvolution. In: IEEE Winter Conference on Applications of Computer Vision (2015)
Schmidt, U., Roth, S.: Shrinkage fields for effective image restoration. In: CVPR (2014)
Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. In: SIGGRAPH (2008)
Sra, S.: Scalable nonconvex inexact proximal splitting. In: NIPS (2012)
Veit, A., Wilber, M., Belongie, S.: Residual networks are exponential ensembles of relatively shallow networks. arXiv e-prints 1605.06431 (2016)
Xu, L., Zheng, S., Jia, J.: Unnatural L0 sparse representation for natural image deblurring. In: CVPR (2013)
Yu, W., Heber, S., Pock, T.: Learning reaction-diffusion models for image inpainting. In: Gall, J., Gehler, P., Leibe, B. (eds.) GCPR 2015. LNCS, vol. 9358, pp. 356–367. Springer, Cham (2015). doi:10.1007/978-3-319-24947-6_29
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. arXiv e-prints 1608.03981 (2016)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for neural networks for image processing. arXiv e-prints 1511.08861 (2015)
Zhu, S.C., Mumford, D.: Prior learning and gibbs reaction-diffusion. TPAMI 19(11), 1236–1250 (1997)
Acknowledgements
We acknowledge grant support from the Austrian Science Fund (FWF) under the START project BIVISION, No. Y729 and the European Research Council under the Horizon 2020 program, ERC starting grant HOMOVIS, No. 640156.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Kobler, E., Klatzer, T., Hammernik, K., Pock, T. (2017). Variational Networks: Connecting Variational Methods and Deep Learning. In: Roth, V., Vetter, T. (eds) Pattern Recognition. GCPR 2017. Lecture Notes in Computer Science(), vol 10496. Springer, Cham. https://doi.org/10.1007/978-3-319-66709-6_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-66709-6_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66708-9
Online ISBN: 978-3-319-66709-6
eBook Packages: Computer ScienceComputer Science (R0)