Deformable Part ModelDeformable Part Model
Presenter : Liu ChangyuAdvisor : Prof. Alex HauptmannInterest : Multimedia Analysis
April 11st, 2013
CMU - Language Technologies Institute 3
1. Research Question1) Object bank is just a image representation for high-level visual tasks, it should be used combing with detailed efficient traning method.2) For difficult tasks, such as extending Object Bank to over 1000 objects and benchmarks of the PASCAL Challenge, it need new traning method to improve the average precision.3) So we want to combine use the part model that proposed at CVPR in 2008.
Introduction
CMU - Language Technologies Institute 4
2. What’s Deformable Part Model?Deformable Part is a discriminatively trained, multiscale model for image training that aim at making possible the effective use of more latent information such as hierarchical (grammar) models and models involving latent three dimensional pose.
Introduction
CMU - Language Technologies Institute 6
Fig. 1 Deformable Part Model
Model--- Deformable Part
The deformable model include both a coarse global template covering an entire object and higher resolution part templates.The templates represent histogram of gradient features
(b1) coarse template (b2)part templates (b3) spatial model (a) person detection Example
CMU - Language Technologies Institute 7
Fig.2 Pyramids of Deformable Part Model
Model---Deformable Part
Fig.2 illustrates a placement of such a model in a HOG pyramid. The root filter location defines the detection window (the pixels inside the cells covered by the filter). The part filters are placed several levels down in the pyramid, so the HOG cells at that level have half the size of cells in the root filter level.
(b)HOG feature pyramid(a) Image pyramid
CMU - Language Technologies Institute 8
Model---Deformable Parts
The score of a placement is given by the scores of each filter (the data term) plus a score of the placement of each part relative to the root (the spatial term),
Where is the w × h × 9 × 4 weight vector are the features in a w×h subwindow of a HOG pyramid. gives the location of the i-th part relative to the root location. ai and bi are two dimensional vectors coefficients for measuring a score for each possible placement of the i-th part.
CMU - Language Technologies Institute 10
LearningLatent SVMsThis model use Latent SVMs to have a classification. As:
where is a vector of model parameters, needed to be learned first, according to:
z is a set of latent values.
CMU - Language Technologies Institute 14
Contents
Introduction Model Algorithm Experiment Conclusion
CMU - Language Technologies Institute 15
1)Experiment has not completed yet, it needed more object models used for deformable part training.
2) Computation need to be speed up.
Conclusion
CMU - Language Technologies Institute 16
Reference
[1] P. Felzenszwalb, D. McAllester, D. Ramanan. A Discriminatively Trained, Multiscale, Deformable Part Model. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008
[2] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection with Discriminatively Trained Part Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 9, Sep. 2010.
[3] Level Image Representation for Scene Classification and Semantic Feature Sparsification. Proceedings of the Neural Information Processing Systems (NIPS), 2010.