Large scale metric learning from equivalence constraints


In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. Often rather tedious optimization procedures are applied that become computationally intractable on a large scale. Further, if one considers the constantly growing amount of data it is often infeasible to specify fully supervised labels for all data points. Instead, it is easier to specify labels in form of equivalence constraints. We introduce a simple though effective strategy to learn a distance metric from equivalence constraints, based on a statistical inference perspective. In contrast to existing methods we do not rely on complex optimization problems requiring computationally expensive iterations. Hence, our method is orders of magnitudes faster than comparable methods. Results on a variety of challenging benchmarks with rather diverse nature demonstrate the power of our method. These include faces in unconstrained environments, matching before unseen object instances and person re-identification across spatially disjoint cameras. In the latter two benchmarks we clearly outperform the state-of-the-art.

DOI: 10.1109/CVPR.2012.6247939

Extracted Key Phrases

8 Figures and Tables

Citations per Year

660 Citations

Semantic Scholar estimates that this publication has 660 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Kstinger2012LargeSM, title={Large scale metric learning from equivalence constraints}, author={Martin K{\"{o}stinger and Martin Hirzer and Paul Wohlhart and Peter M. Roth and Horst Bischof}, journal={2012 IEEE Conference on Computer Vision and Pattern Recognition}, year={2012}, pages={2288-2295} }