Geometry-aware deep transform

Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning methods mostly relies on an enormous volume of labeled training samples to learn a huge number of parameters in a network, therefore, understanding the generalization ability of a learned deep network cannot be overlooked, especially when restricted to a small training set, which is the case for many applications. In this paper, we propose a novel deep learning objective formulation that unifies both the classification and metric learning criteria. We then introduce a geometry-aware deep transform to enable a non-linear discriminative and robust feature transform, which shows competitive performance on small training sets for both synthetic and real-world data. We further support the proposed framework with a formal (K)-robustness analysis.

Original languageEnglish (US)
Title of host publication2015 International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4139-4147
Number of pages9
ISBN (Electronic)9781467383912
DOIs
StatePublished - Feb 17 2015
Externally publishedYes
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: Dec 11 2015Dec 18 2015

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)1550-5499

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
Country/TerritoryChile
CitySantiago
Period12/11/1512/18/15

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Geometry-aware deep transform'. Together they form a unique fingerprint.

Cite this