Abstract
It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision. Recent years have seen the emergence of two main approaches for learning the parameters in MRFs: (1) probabilistic learning using sampling-based algorithms and (2) loss-specific training based on MAP estimate. After investigating existing training approaches, it turns out that the performance of the loss-specific training has been significantly underestimated in existing work. In this paper, we revisit this approach and use techniques from bi-level optimization to solve it. We show that we can get a substantial gain in the final performance by solving the lower-level problem in the bi-level framework with high accuracy using our newly proposed algorithm. As a result, our trained model is on par with highly specialized image denoising algorithms and clearly outperforms probabilistically trained MRF models. Our findings suggest that for the loss-specific training scheme, solving the lower-level problem with higher accuracy is beneficial. Our trained model comes along with the additional advantage, that inference is extremely efficient. Our GPU-based implementation takes less than 1s to produce state-of-the-art performance.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Barbu, A.: Training an active random field for real-time image denoising. IEEE Trans. on Image Proc. 18(11), 2451–2462 (2009)
Colson, B., Marcotte, P., Savard, G.: An overview of bilevel optimization. Annals OR 153(1), 235–256 (2007)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.O.: Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. on Image Proc. 16(8), 2080–2095 (2007)
Domke, J.: Generic methods for optimization-based modeling. Journal of Machine Learning Research - Proceedings Track 22, 318–326 (2012)
Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. on Image Proc. 15(12), 3736–3745 (2006)
Gao, Q., Roth, S.: How well do filter-based MRFs model natural images? In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds.) DAGM and OAGM 2012. LNCS, vol. 7476, pp. 62–72. Springer, Heidelberg (2012)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Computation 14(8), 1771–1800 (2002)
Huang, J., Mumford, D.: Statistics of natural images and models. In: CVPR, Fort Collins, CO, USA, pp. 541–547 (1999)
Jancsary, J., Nowozin, S., Rother, C.: Loss-specific training of non-parametric image restoration models: A new state of the art. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 112–125. Springer, Heidelberg (2012)
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Mathematical Programming 45(1), 503–528 (1989)
Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Non-local sparse models for image restoration. In: ICCV, pp. 2272–2279 (2009)
Peyré, G., Fadili, J.: Learning analysis sparsity priors. In: Proc. of Sampta 2011 (2011), http://hal.archives-ouvertes.fr/hal-00542016/
Roth, S., Black, M.J.: Fields of experts. International Journal of Computer Vision 82(2), 205–229 (2009)
Samuel, K.G.G., Tappen, M.: Learning optimized MAP estimates in continuously-valued MRF models. In: CVPR (2009)
Schmidt, U., Gao, Q., Roth, S.: A generative perspective on MRFs in low-level vision. In: CVPR, pp. 1751–1758 (2010)
Schmidt, U., Schelten, K., Roth, S.: Bayesian deblurring with integrated noise estimation. In: CVPR, pp. 2625–2632 (2011)
Tappen, M.F., Liu, C., Adelson, E.H., Freeman, W.T.: Learning gaussian conditional random fields for low-level vision. In: CVPR, pp. 1–8 (2007)
Tappen, M.F.: Utilizing variational optimization to learn markov random fields. In: CVPR, pp. 1–8 (2007)
Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: CVPR (2007)
Zhang, H., Zhang, Y., Li, H., Huang, T.S.: Generative bayesian image super resolution with natural image prior. IEEE Trans. on Image Proc. 21(9), 4054–4067 (2012)
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: ICCV, pp. 479–486 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, Y., Pock, T., Ranftl, R., Bischof, H. (2013). Revisiting Loss-Specific Training of Filter-Based MRFs for Image Restoration. In: Weickert, J., Hein, M., Schiele, B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40602-7_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-40602-7_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40601-0
Online ISBN: 978-3-642-40602-7
eBook Packages: Computer ScienceComputer Science (R0)