Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections

Abstract

Association field models have been used to explain human contour grouping performance and to explain the mean frequency of long-range horizontal connections across cortical columns in V1. However, association fields essentially depend on pairwise statistics of edges in natural scenes. We develop a spectral test of the sufficiency of pairwise statistics and show that there is significant higher-order structure. An analysis using a probabilistic spectral embedding reveals curvature-dependent components to the association field, and reveals a challenge for biological learning algorithms.

Cite

Text

Lawlor and Zucker. "Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections." Neural Information Processing Systems, 2013.

Markdown

[Lawlor and Zucker. "Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections." Neural Information Processing Systems, 2013.](https://mlanthology.org/neurips/2013/lawlor2013neurips-thirdorder/)

BibTeX

@inproceedings{lawlor2013neurips-thirdorder,
  title     = {{Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections}},
  author    = {Lawlor, Matthew and Zucker, Steven W},
  booktitle = {Neural Information Processing Systems},
  year      = {2013},
  pages     = {1763-1771},
  url       = {https://mlanthology.org/neurips/2013/lawlor2013neurips-thirdorder/}
}