Structured output-associative regression

Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language processing or computational biology. This motivates the learning of functional dependencies between spaces with complex, interdependent inputs and outputs, as arising e.g. from images and their corresponding 3d scene representations. In this spirit, we propose a new structured learning method-Structured Output-Associative Regression (SOAR)-that models not only the input-dependency but also the self-dependency of outputs, in order to provide an output re-correlation mechanism that complements the (more standard) input-based regressive prediction. The model is simple but powerful, and, in principle, applicable in conjunction with any existing regression algorithms. SOAR can be kernelized to deal with non-linear problems and learning is efficient via primal/dual formulations not unlike ones used for kernel ridge regression or support vector regression. We demonstrate that the method outperforms weighted nearest neighbor and regression methods for the reconstruction of images of handwritten digits and for 3D human pose estimation from video in the HumanEva benchmark.

[1]  R. Cook.  Regression Graphics , 1994 .

[2]  Alexander Gammerman,et al.  Ridge Regression Learning Algorithm in Dual Variables , 1998, ICML.

[3]  David Maxwell Chickering,et al.  Dependency Networks for Inference, Collaborative Filtering, and Data Visualization , 2000, J. Mach. Learn. Res..

[4]  D. Heckerman,et al.  Dependency networks for inference , 2000 .

[5]  Rómer Rosales,et al.  Learning Body Pose via Specialized Maps , 2001, NIPS.

[6]  Bernhard Schölkopf,et al.  Kernel Dependency Estimation , 2002, NIPS.

[7]  Martial Hebert,et al.  Discriminative Fields for Modeling Spatial Dependencies in Natural Images , 2003, NIPS.

[8]  Trevor Darrell,et al.  Fast pose estimation with parameter-sensitive hashing , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[10]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[11]  Bernhard Schölkopf,et al.  Joint Kernel Maps , 2005, IWANN.

[12]  Jason Weston,et al.  A general regression technique for learning transductions , 2005, ICML '05.

[13]  Cristian Sminchisescu,et al.  Conditional Visual Tracking in Kernel Space , 2005, NIPS.

[14]  Charles A. Micchelli,et al.  On Learning Vector-Valued Functions , 2005, Neural Computation.

[15]  Thomas Hofmann,et al.  Large Margin Methods for Structured and Interdependent Output Variables , 2005, J. Mach. Learn. Res..

[16]  Chih-Jen Lin,et al.  Working Set Selection Using Second Order Information for Training Support Vector Machines , 2005, J. Mach. Learn. Res..

[17]  Michael J. Black,et al.  Predicting 3D People from 2D Pictures , 2006, AMDO.

[18]  Cristian Sminchisescu,et al.  Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[20]  Ankur Agarwal,et al.  Recovering 3D human pose from monocular images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Ronald Poppe,et al.  Evaluating Example-based Pose Estimation: Experiments on the HumanEva Sets , 2007 .

[22]  Andrew W. Fitzgibbon,et al.  The Joint Manifold Model for Semi-supervised Multi-valued Regression , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[23]  Michael I. Jordan,et al.  Regression on manifolds using kernel dimension reduction , 2007, ICML '07.

[24]  Vladimir Pavlovic,et al.  Dimensionality reduction using covariance operator inverse regression , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Christoph H. Lampert,et al.  Learning to Localize Objects with Structured Output Regression , 2008, ECCV.

[26]  Cristian Sminchisescu,et al.  Twin Gaussian Processes for Structured Prediction , 2010, International Journal of Computer Vision.

[27]  Cristian Sminchisescu,et al.  Fast algorithms for large scale conditional 3D prediction , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.