Deep nonlinear metric learning with independent subspace analysis for face verification

Explore this paper's citation graph

Summary

This work proposes a nonlinear metric learning method, which learns an explicit mapping from the original space to an optimal subspace, using deep Independent Subspace Analysis network, and exhibits more powerful ability to learn the nature of highly variable dataset.

Type
article
Published
2012-10-29
Cited by
77
References
17

Keywords

Metric (unit), Mahalanobis distance, Artificial intelligence, Computer science, Subspace topology

References

Cited by

Related papers