Projects per year
Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Publisher | . |
Pages | 2288-2295 |
DOIs | |
Publication status | Published - 2012 |
Fields of Expertise
- Information, Communication & Computing
Projects
- 2 Finished
-
SHARE - Steiermark Hybrid Advanced Road Efficiency- Emission optimising in local adaptive traffic signal control and tactical driving in public transport
Roth, P., Fellendorf, M., Haberl, M. & Bischof, H.
1/07/11 → 31/12/13
Project: Research project
-
FWF - Advanced Learning Tracking - Advanced Learning for Tracking and Detection in Medical Workflow Analysis
Schulter, S., Sternig, S., Köstinger, M., Wohlhart, P. & Bischof, H.
1/07/11 → 30/06/15
Project: Research project
Activities
- 1 Poster presentation
-
Poster Presentation: Large Scale Metric Learning from Equivalence Constraints
Martin Hirzer (Speaker)
18 Jun 2012 → 20 Jun 2012Activity: Talk or presentation › Poster presentation › Science to science