English

Geometry-aware Deep Transform

Computer Vision and Pattern Recognition 2015-10-20 v2

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,ϵ)(K,\epsilon)-robustness analysis.

Keywords

Cite

@article{arxiv.1509.05360,
  title  = {Geometry-aware Deep Transform},
  author = {Jiaji Huang and Qiang Qiu and Robert Calderbank and Guillermo Sapiro},
  journal= {arXiv preprint arXiv:1509.05360},
  year   = {2015}
}

Comments

to appear in ICCV2015, updated with minor revision

R2 v1 2026-06-22T10:59:09.157Z