html5-img
1 / 16

Presenter : You Lin Chen Authors : Huicheng Zheng, Member, IEEE, Grégoire Lefebvre,

Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-Based Invariant Image Feature Construction. Presenter : You Lin Chen Authors : Huicheng Zheng, Member, IEEE, Grégoire Lefebvre, and Christophe Laurent. 2007.WI.7. Outline. Motivation

nizana
Download Presentation

Presenter : You Lin Chen Authors : Huicheng Zheng, Member, IEEE, Grégoire Lefebvre,

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Fast-Learning Adaptive-Subspace Self-Organizing Map: An Application to Saliency-BasedInvariant Image Feature Construction Presenter : You Lin Chen Authors : Huicheng Zheng, Member, IEEE, Grégoire Lefebvre, and Christophe Laurent 2007.WI.7

  2. Outline • Motivation • Objective • Methodology • Experiments • Conclusion • Comments

  3. Motivation The traditional learning procedure of the ASSOM involves computations related to a rotation operator matrix. The rotation computations which not only is memory demanding, but also has computational load quadratic to the input dimension.

  4. 2 4.8 3.3 22+4.82+3.32

  5. Objectives In this paper will show that in the ASSOM learning which leads to a computational load linear to both the input dimension and the subspace dimension. we are also interested in applying ASSOM to saliency-based invariant feature construction for image classification.

  6. Methodology_1 Kohonen’s ASSOM learning algorithm

  7. Methodology_1

  8. Methodology_1 Robbins–Monro stochastic approximation

  9. Methodology_1 BFL-ASSOM ASSOM BFL-ASSOM FL-ASSOM

  10. Experiments_1 The input episodes are generated by filtering a whitenoise image with a second-order Butterworth filter. The cutoff frequency isset to 0.6 times the Nyquist frequency of the sampling lattice.

  11. Experiments_1

  12. Methodology_2

  13. Methodology_2

  14. Experiments_2

  15. Conclusion • The ASSOMis useful for dimension reduction, invariant feature generation, and visualization. • BFL-ASSOM, where the increment of each basis vector is a linear combination of the component vectors in the input episode. • The SPMAS showed promising performance on a ten-category image classification problem

  16. Comments • Advantage • … • Drawback • … • Application • …

More Related