Spotlight the Negatives: A Generalized Discriminative Latent Model

Discriminative latent variable models (LVM) are frequently applied to various visual recognition tasks. In these systems the latent (hidden) variables provide a formalism for modeling structured variation of visual features. Conventionally, latent variables are de- fined on the variation of the foreground (positive) class. In this work we augment LVMs to include negative latent variables corresponding to the background class. We formalize the scoring function of such a generalized LVM (GLVM). Then we discuss a framework for learning a model based on the GLVM scoring function. We theoretically showcase how some of the current visual recognition methods can benefit from this generalization. Finally, we experiment on a generalized form of Deformable Part Models with negative latent variables and show significant improvements on two different detection tasks.

[1]  Ivan Laptev,et al.  Object Detection Using Strongly-Supervised Deformable Part Models , 2012, ECCV.

[2]  Jitendra Malik,et al.  Poselets: Body part detectors trained using 3D human pose annotations , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Alan L. Yuille,et al.  The Concave-Convex Procedure , 2003, Neural Computation.

[4]  Yong Jae Lee,et al.  AverageExplorer: interactive exploration and alignment of visual data collections , 2014, ACM Trans. Graph..

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

[6]  Yang Wang,et al.  Kernel Latent SVM for Visual Recognition , 2012, NIPS.

[7]  Christopher M. Brown.  Inherent Bias and Noise in the Hough Transform , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Luc Van Gool,et al.  Latent Hough Transform for Object Detection , 2012, ECCV.

[9]  Derek Hoiem,et al.  Learning Collections of Part Models for Object Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  C. V. Jawahar,et al.  Cats and dogs , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Derek Hoiem,et al.  Diagnosing Error in Object Detectors , 2012, ECCV.

[12]  Timothy F. Cootes,et al.  Comparing Active Shape Models with Active Appearance Models , 1999, BMVC.

[13]  Andrew Zisserman,et al.  Automatic Discovery and Optimization of Parts for Image Classification , 2015, ICLR.

[14]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  C. V. Jawahar,et al.  Blocks That Shout: Distinctive Parts for Scene Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Pedro F. Felzenszwalb.  Object detection grammars , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[17]  Jitendra Malik,et al.  Deformable part models are convolutional neural networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Yunde Jia,et al.  Discriminatively Trained And-Or Tree Models for Object Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Long Zhu,et al.  Learning a Hierarchical Deformable Template for Rapid Deformable Object Parsing , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Alexei A. Efros,et al.  Mid-level Visual Element Discovery as Discriminative Mode Seeking , 2013, NIPS.

[21]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[22]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.