The use of deep learning features in a hierarchical classifier learned with the minimization of a non-greedy loss function that delays gratification

Files

RA_hdl_107656.pdf (3.31 MB)
  (Restricted Access)

Date

2015

Authors

Liao, Z.
Carneiro, G.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings / ICIP ... International Conference on Image Processing, 2015, vol.2015-December, pp.4540-4544

Statement of Responsibility

Zhibin Liao and Gustavo Carneiro

Conference Name

IEEE International Conference on Image Processing (ICIP) (27 Sep 2015 - 30 Sep 2015 : Quebec City, CANADA)

Abstract

Recently, we have observed the traditional feature representations are being rapidly replaced by the deep learning representations, which produce significantly more accurate classification results when used together with the linear classifiers. However, it is widely known that non-linear classifiers can generally provide more accurate classification but at a higher computational cost involved in their training and testing procedures. In this paper, we propose a new efficient and accurate non-linear hierarchical classification method that uses the aforementioned deep learning representations. In essence, our classifier is based on a binary tree, where each node is represented by a linear classifier trained using a loss function that minimizes the classification error in a non-greedy way, in addition to postponing hard classification problems to further down the tree. In comparison with linear classifiers, our training process increases only marginally the training and testing time complexities, while showing competitive classification accuracy results. In addition, our method is shown to generalize better than shallow non-linear classifiers. Empirical validation shows that the proposed classifier produces more accurate classification results when compared to several linear and non-linear classifiers on Pascal VOC07 database.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2015 IEEE

License

Call number

Persistent link to this record