Coarse-to-Fine Minimization of Some Common Nonconvexities

The continuation method is a popular heuristic in computer vision for nonconvex optimization. The idea is to start from a simplified problem and gradually deform it to the actual problem while tracking the solution. There are many choices for how to map the nonconvex objective to some convex task. One popular principle for such construction is Gaussian smoothing of the objective function. This involves an integration which may be expensive to compute numerically. We argue that often simple tricks at the problem formulation plus some mild approximations can make the resulted task amenable to closed form integral.

[1]  Hossein Mobahi,et al.  Seeing through the blur , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  F. Janabi-Sharifi,et al.  Peak stick RBF network for online system identification , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[3]  Fernando De la Torre,et al.  Gaussian Processes Multiple Instance Learning , 2010, ICML.

[4]  Pascal Frossard,et al.  Analysis of Descent-Based Image Registration , 2013, SIAM J. Imaging Sci..

[5]  Michael J. Black,et al.  On the unification of line processes, outlier rejection, and robust statistics with applications in early vision , 1996, International Journal of Computer Vision.

[6]  Peter V. Gehler,et al.  Deterministic Annealing for Multiple-Instance Learning , 2007, AISTATS.

[7]  Daniel Cremers,et al.  Convex Relaxation of Vectorial Problems with Coupled Regularization , 2014, SIAM J. Imaging Sci..

[8]  Demetri Terzopoulos,et al.  The Computation of Visible-Surface Representations , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

[10]  Marc Levoy,et al.  Zippered polygon meshes from range images , 1994, SIGGRAPH.

[11]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[12]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[13]  Marc Levoy,et al.  Fitting smooth surfaces to dense polygon meshes , 1996, SIGGRAPH.

[14]  Hossein Mobahi,et al.  On the Link between Gaussian Homotopy Continuation and Convex Envelopes , 2015, EMMCVPR.

[15]  AraabiBabak Nadjar,et al.  A BIOLOGICALLY INSPIRED METHOD FOR CONCEPTUAL IMITATION USING REINFORCEMENT LEARNING , 2007 .

[16]  George Siemens,et al.  Current state and future trends: a citation network analysis of the learning analytics field , 2014, LAK.

[17]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[18]  Hossein Mobahi,et al.  Fuzzy perception, emotion and expression for interactive robots , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[19]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[20]  S. Sathiya Keerthi,et al.  Deterministic annealing for semi-supervised kernel machines , 2006, ICML.

[21]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[22]  Hossein Mobahi,et al.  HCI Applications for aiding children with mental disorders , 2005, CROS.

[23]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[24]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[25]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[26]  Geoffrey E. Hinton,et al.  Learning Generative Texture Models with extended Fields-of-Experts , 2009, BMVC.

[27]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[28]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[30]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Daniel Cremers,et al.  Tight Convex Relaxations for Vector-Valued Labeling , 2013, SIAM J. Imaging Sci..

[32]  Layne T. Watson,et al.  Theory of Globally Convergent Probability-One Homotopies for Nonlinear Programming , 2000, SIAM J. Optim..

[33]  Pascal Vincent,et al.  The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training , 2009, AISTATS.

[34]  Mads Nielsen,et al.  Graduated Non-Convexity by Smoothness Focusing , 1993, BMVC.

[35]  Michael J. Black,et al.  Secrets of optical flow estimation and their principles , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[36]  Jitendra Malik,et al.  Color Constancy, Intrinsic Images, and Shape Estimation , 2012, ECCV.

[37]  Jitendra Malik,et al.  Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Hossein Mobahi,et al.  Data-driven image completion by image patch subspaces , 2009, 2009 Picture Coding Symposium.

[39]  Swarm contours: A fast self-organization approach for snake initialization , 2006, Complex..

[40]  Jason Weston,et al.  Deep learning via semi-supervised embedding , 2008, ICML '08.

[41]  S. Sathiya Keerthi,et al.  Deterministic Annealing for Semi-Supervised Structured Output Learning , 2012, AISTATS.

[42]  Guillermo Sapiro,et al.  Online dictionary learning for sparse coding , 2009, ICML '09.