Navigation

Large Scale Metric Learning from Equivalence Constraints*

Martin Köstinger, Martin Hirzer, Paul Wohlhart, Peter M. Roth, Horst Bischof
Institute for Computer Graphics and Vision, Graz University of Technology

* The work was supported by the Austrian Science Foundation (FWF) project Advanced Learning for Tracking and Detection in Medical Workflow Analysis (I535-N23) and by the Austrian Research Promotion Agency (FFG) project SHARE in the IV2Splus program.






Content

This page briefly describes our work on large-scale similarity computation.

It provides:

Prerequisites to run the code:

Full Text

PDF, POSTER

Citation

@INPROCEEDINGS{lrs:icg:koestinger12a,
    author = {Martin Koestinger and Martin Hirzer and Paul Wohlhart and Peter M. Roth and Horst Bischof},
    title = {Large Scale Metric Learning from Equivalence Constraints},
    booktitle = {Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition}},
    year = {2012},
}

Datasets and Results

To check out the result figures where we benchmark our method (KISSME) to related work click here (LFW, ToyCars, VIPeR, PubFig). The biggest benefit is the speedup in training compared to related approaches.

Documentation

The best thing is to check out the inline documentation of the matlab files. For all experiments a main file (LFW, ToyCars, VIPeR, PubFig) describes the used features and database. Our method is described in LearnAlgoKISSME.m, in particular in the learnPairWise method.

Instructions for reproducing experiments

In order to run the experiments presented in this paper, we assume basic knowlege of Matlab. The code is tested under Linux (x64) and Windows (x32,x64), should also work on other platforms with minor modifications. Reproducing the results of our method should not take more than five minutes, including installation.

Grabbing the Code & Data

To download and unpack the needed files run the following code snipet in Matlab. Alternatively, click the links; download and unpack the archives to a directory of your choice.

BASE_DIR = cd;
unzip('http://lrs.icg.tugraz.at/research/kissme/kissme.zip',BASE_DIR); %(0.03 MB)
unzip('http://lrs.icg.tugraz.at/research/kissme/kissme_features_basic.zip',BASE_DIR); %(54.68 MB)

The provided features cover everything that is needed to reproduce the experiments. If you want to use the original extracted features (before PCA compression) download the kissme_features_full.zip (887.11 MB) archive.

Installing other competing metric learning methods...

The experiments described in the paper benchmark our method (KISSME) to other metric learning methods (LMNN,ITML,LDML,SVMs). Due to different licenses these are not pre-installed by default. If you agree to these install the code with the following matlab snipet. For details click on the link below.

run(fullfile(BASE_DIR,'KISSME','toolbox','install3dpartylibs.m'));

Quick Start Running Experiments

Change the directory to KISSME, workflows, CVPR.

cd(fullfile(BASE_DIR,'KISSME','workflows','CVPR'));

Pick the experiment of your choice and run the according script, i.e. demo_viper.m.

To run all experiments ...

% ToyCars, VIPeR
run(fullfile(cd,'demo_toycars.m'));
run(fullfile(cd,'demo_viper.m'));

% PubFig, LFW
run(fullfile(cd,'demo_pubfig.m'));
run(fullfile(cd,'demo_lfw_sift.m'));
run(fullfile(cd,'demo_lfw_attributes.m'));

Note: For LFW and PubFig only KISSME is enabled per default. For some of the other algorithms it takes quite long to complete. If you want to train all installed learning algorithms uncomment the respective code. Check the inline comments for details, e.g. in demo_lfw_sift.m.

License

The toolbox code is licensed under the BSD 3-Clause License ("modified BSD license"). If you use the code, i.e. our algorithm in a scientific publication please cite this paper. For the provided data please check the included copyright notice as it is partly based on other data.

References

[1]   L. M. Bregman. The Relaxation Method of Finding the Common Point of Convex Sets and Its Application to the Solution of Problems in Convex Programming. USSR Computational Mathematics and Mathematical Physics, 7:200-217, 1967.

[2]   C.-C. Chang and C.-J. Lin. LIBSVM: A library for support vector machines. ACM Trans. on Intelligent Systems and Technology, 2:27:1-27:27, 2011.

[3]   J. V. Davis, B. Kulis, P. Jain, S. Sra, and I. S. Dhillon. Information-theoretic metric learning. In Proc. IEEE Intern. Conf. on Machine Learning, 2007.

[4]   M. Dikmen, E. Akbas, T. S. Huang, and N. Ahuja. Pedestrian recognition with a learned metric. In Proc. Asian Conf. on Computer Vision, 2010.

[5]   M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani. Person re-identification by symmetry-driven accumulation of local features. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2010.

[6]   D. Gray, S. Brennan, and H. Tao. Evaluating appearance models for recongnition, reacquisition and tracking. In Proc. IEEE Intern. Workshop on Performance Evaluation of Tracking and Surveillance, 2007.

[7]   D. Gray and H. Tao. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Proc. European Conf. on Computer Vision, 2008.

[8]   M. Guillaumin, J. Verbeek, and C. Schmid. Is that you? Metric learning approaches for face identification. In Proc. IEEE Intern. Conf. on Computer Vision, 2009.

[9]   M. Guillaumin, J. Verbeek, and C. Schmid. Multiple instance metric learning from automatically labeled bags of faces. In Proc. European Conf. on Computer Vision, 2010.

[10]   M. Hirzer, C. Beleznai, P. Roth, and H. Bischof. Person re-identification by descriptive and discriminative classification. In Proc. Scandinavian Conf. on Image Analysis, 2011.

[11]   S. C. Hoi, W. Liu, M. R. Lyu, and W.-Y. Ma. Learning distance metrics with contextual constraints for image retrieval. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2006.

[12]   G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, 2007.

[13]   N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and Simile Classifiers for Face Verification. In Proc. IEEE Intern. Conf. on Computer Vision, 2009.

[14]   D. Lowe. Distinctive image features from scale-invariant keypoints. Intern. Journal of Computer Vision, 60(2):91-110, 2004.

[15]   E. Nowak and F. Jurie. Learning visual similarity measures for comparing never seen objects. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2007.

[16]   T. Ojala, M. Pietikänien, and T. Mäenpä. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. on PAMI, 24(7):971-987, 2002.

[17]   B. Prosser, W.-S. Zheng, S. Gong, and T. Xiang. Person re-identification by support vector ranking. In Proc. British Machine Vision Conf., pages 21.1-21.11, 2010.

[18]   X. Wang, G. Doretto, T. B. Sebastian, J. Rittscher, and P. H. Tu. Shape and appearance context modeling. In Proc. IEEE Intern. Conf. on Computer Vision, 2007.

[19]   K. Q. Weinberger, J. Blitzer, and L. K. Saul. Distance metric learning for large margin nearest neighbor classification. In Advances NIPS, 2006.

[20]   K. Q. Weinberger and L. K. Saul. Fast solvers and efficient implementations for distance metric learning. In Proc. IEEE Intern. Conf. on Machine Learning, 2008.

[21]   J. Ye, Z. Zhao, and H. Liu. Adaptive distance metric learning for clustering. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2007.

[22]   J. Yu, J. Amores, N. Sebe, and Q. Tian. Toward robust distance metric analysis for similarity estimation. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2006.

[23]   W.-S. Zheng, S. Gong, and T. Xiang. Person re-identification by probabilistic relative distance comparison. In Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition, 2011.

Copyright 2010 ICG

Valid XHTML 1.1 Valid CSS