Share Email Print

Proceedings Paper

Visual discrimination and adaptation using non-linear unsupervised learning
Author(s): Sandra Jiménez; Valero Laparra; Jesus Malo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Understanding human vision not only involves empirical descriptions of how it works, but also organization principles that explain why it does so. Identifying the guiding principles of visual phenomena requires learning algorithms to optimize specific goals. Moreover, these algorithms have to be flexible enough to account for the non-linear and adaptive behavior of the system. For instance, linear redundancy reduction transforms certainly explain a wide range of visual phenomena. However, the generality of this organization principle is still in question:10 it is not only that and additional constraints such as energy cost may be relevant as well, but also, statistical independence may not be the better solution to make optimal inferences in squared error terms. Moreover, linear methods cannot account for the non-uniform discrimination in different regions of the image and color space: linear learning methods necessarily disregard the non-linear nature of the system. Therefore, in order to account for the non-linear behavior, principled approaches commonly apply the trick of using (already non-linear) parametric expressions taken from empirical models. Therefore these approaches are not actually explaining the non-linear behavior, but just fitting it to image statistics. In summary, a proper explanation of the behavior of the system requires flexible unsupervised learning algorithms that (1) are tunable to different, perceptually meaningful, goals; and (2) make no assumption on the non-linearity. Over the last years we have worked on these kind of learning algorithms based on non-linear ICA,18 Gaussianization, 19 and principal curves. In this work we stress the fact that these methods can be tuned to optimize different design strategies, namely statistical independence, error minimization under quantization, and error minimization under truncation. Then, we show (1) how to apply these techniques to explain a number of visual phenomena, and (2) suggest the underlying organization principle in each case.

Paper Details

Date Published: 14 March 2013
PDF: 6 pages
Proc. SPIE 8651, Human Vision and Electronic Imaging XVIII, 86511I (14 March 2013); doi: 10.1117/12.2019008
Show Author Affiliations
Sandra Jiménez, Univ. de València (Spain)
Valero Laparra, Univ. de València (Spain)
Jesus Malo, Univ. de València (Spain)

Published in SPIE Proceedings Vol. 8651:
Human Vision and Electronic Imaging XVIII
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Huib de Ridder, Editor(s)

© SPIE. Terms of Use
Back to Top