Latent structural SVM with marginal probabilities for weakly labeled structured learning

In the last years, the increasing availability of annotated data has facilitated the great success of supervised learning in real-world applications such as semantic labeling. However, the vast majority of data is nowadays unlabeled or partially annotated. In this paper, we develop an Expected Marginal Latent Structural SVM (EM-LSSVM) framework for performing structured learning in the presence of weakly (partially) annotated data by incorporating the uncertainty of the unobserved data as marginals. Experimental results on semantic labeling show the potential of the proposed method. In particular, we learn the parameters of a CRF where large amounts of noisy and unobserved data are available. Comparison against state of the art demonstrates the applicability of our algorithm to practical applications.

[1]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[2]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Wei Ping,et al.  Marginal Structured SVM with Hidden Variables , 2014, ICML.

[4]  Thorsten Joachims,et al.  Learning structural SVMs with latent variables , 2009, ICML '09.

[5]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[6]  Derek Hoiem,et al.  Learning CRFs Using Graph Cuts , 2008, ECCV.

[7]  Marc Pollefeys,et al.  Efficient Structured Prediction with Latent Variables for General Graphical Models , 2012, ICML.

[8]  Matthieu Cord,et al.  Incremental learning of latent structural SVM for weakly supervised image classification , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[9]  Guosheng Lin,et al.  CRF Learning with CNN Features for Image Segmentation , 2015, Pattern Recognit..

[10]  Justin Domke,et al.  Learning Graphical Model Parameters with Approximate Marginal Inference , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  FuaPascal,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012 .

[12]  Thorsten Joachims,et al.  Cutting-plane training of structural SVMs , 2009, Machine Learning.

[13]  Joost van de Weijer,et al.  Harmony potentials for joint classification and segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Pascal Fua,et al.  Structured Image Segmentation Using Kernelized Features , 2012, ECCV.

[15]  Rainer Lienhart,et al.  Automatic object annotation from weakly labeled data with latent structured SVM , 2014, 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI).

[16]  Greg Mori,et al.  Max-margin hidden conditional random fields for human action recognition , 2009, CVPR.

[17]  Martin J. Wainwright,et al.  Estimating the "Wrong" Graphical Model: Benefits in the Computation-Limited Setting , 2006, J. Mach. Learn. Res..

[18]  Qiang Liu,et al.  Variational algorithms for marginal MAP , 2011, J. Mach. Learn. Res..

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

[20]  Vladlen Koltun,et al.  Parameter Learning and Convergent Inference for Dense Random Fields , 2013, ICML.

[21]  Christoph H. Lampert,et al.  A multi-plane block-coordinate frank-wolfe algorithm for training structural SVMs with a costly max-oracle , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Lars Petersson,et al.  Classification of natural scene multi spectral images using a new enhanced CRF , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[24]  Joost van de Weijer,et al.  Harmony Potentials , 2011, International Journal of Computer Vision.

[25]  Antonio Criminisi,et al.  TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context , 2007, International Journal of Computer Vision.

[26]  Matthieu Cord,et al.  MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Trevor Darrell,et al.  Hidden Conditional Random Fields , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[29]  Bill Triggs,et al.  Scene Segmentation with CRFs Learned from Partially Labeled Images , 2007, NIPS.