QuaLam11.pdf (395.92 kB)
Learning multi-view neighborhood preserving projections
conference contribution
posted on 2023-06-08, 16:45 authored by Novi QuadriantoNovi Quadrianto, Christoph LampertWe address the problem of metric learning for multi-view data, namely the construction of embedding projections from data in different representations into a shared feature space, such that the Euclidean distance in this space provides a meaningful within-view as well as between-view similarity. Our motivation stems from the problem of cross-media retrieval tasks, where the availability of a joint Euclidean distance function is a prerequisite to allow fast, in particular hashing-based, nearest neighbor queries. We formulate an objective function that expresses the intuitive concept that matching samples are mapped closely together in the output space, whereas non-matching samples are pushed apart, no matter in which view they are available. The resulting optimization problem is not convex, but it can be decomposed explicitly into a convex and a concave part, thereby allowing efficient optimization using the convex-concave procedure. Experiments on an image retrieval task show that nearest-neighbor based cross-view retrieval is indeed possible, and the proposed technique improves the retrieval accuracy over baseline techniques.
History
Publication status
- Published
File Version
- Accepted version
Journal
Proceedings of the 28 th International Conference on Machine Learning; Washington, USA; 28 June - 2 July 2011Publisher
Association for Computing MachineryPublisher URL
Page range
425-432Place of publication
New YorkISBN
9781450306195Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Editors
Tobias Scheffer, Lise GetoorLegacy Posted Date
2014-02-24First Open Access (FOA) Date
2017-06-16First Compliant Deposit (FCD) Date
2017-06-16Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC