Institute Homepage
Institute Homepage DE Sign In

Back

Empirical Inference Poster 2006

Learning Eye Movements

Web
Thumb ticker sm l1170153
Empirical Inference
Bernhard Schölkopf
  • Director
no image
Empirical Inference
Wolf Kienzle
Thumb ticker sm thumb felix a. wichmann
Empirical Inference
Felix A. Wichmann
  • Research Scientist

The human visual system samples images through saccadic eye movements which rapidly change the point of fixation. Although the selection of eye movement targets depends on numerous top-down mechanisms, a number of recent studies have shown that low-level image features such as local contrast or edges play an important role. These studies typically used predefined image features which were afterwards experimentally verified. Here, we follow a complementary approach: instead of testing a set of candidate image features, we infer these hypotheses from the data, using methods from statistical learning. To this end, we train a non-linear classifier on fixated vs. randomly selected image patches without making any physiological assumptions. The resulting classifier can be essentially characterized by a nonlinear combination of two center-surround receptive fields. We find that the prediction performance of this simple model on our eye movement data is indistinguishable from the physiologically motivated model of Itti & Koch (2000) which is far more complex. In particular, we obtain a comparable performance without using any multi-scale representations, long-range interactions or oriented image features.

Author(s): Kienzle, W. and Wichmann, FA. and Schölkopf, B. and Franz, MO.
Links:
Journal: Sensory Coding And The Natural Environment
Volume: 2006
Pages: 1
Year: 2006
Month: September
Day: 0
BibTeX Type: Poster (poster)
Digital: 0
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

BibTeX 

@poster{4154,
  title = {Learning Eye Movements},
  journal = {Sensory Coding And The Natural Environment},
  abstract = {The human visual system samples images through saccadic eye movements which rapidly change the point of fixation. Although the selection of eye movement targets depends on numerous top-down mechanisms, a number of recent studies have shown that low-level image features such as local contrast or edges play an important role. These studies typically used predefined image features which were afterwards experimentally verified.
  Here, we follow a complementary approach: instead of testing a set of candidate image features, we infer these hypotheses from the data, using methods from statistical learning. To this end, we train a non-linear classifier on fixated vs. randomly selected image patches without making any physiological assumptions. The resulting classifier can be essentially characterized by a nonlinear combination of two center-surround receptive fields. We find that the prediction performance of this simple model on our eye movement data is indistinguishable from the physiologically motivated model of Itti & Koch (2000) which is far more complex. In particular, we obtain a comparable performance without using any multi-scale representations, long-range interactions or oriented image features.},
  volume = {2006},
  pages = {1},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = sep,
  year = {2006},
  author = {Kienzle, W. and Wichmann, FA. and Sch{\"o}lkopf, B. and Franz, MO.},
  month_numeric = {9}
}