A Rotation and Translation Invariant Discrete Saliency Network
Abstract
We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input provided to V1 by LGN, the in- put to our computation is isotropic. That is, the input is composed of spots not edges. Second, our network computes a well defined function of the input based on a distribution of closed contours characterized by a random process. Third, even though our computation is implemented in a discrete network, its output is invariant to continuous rotations and translations of the input pattern.
Cite
Text
Williams and Zweck. "A Rotation and Translation Invariant Discrete Saliency Network." Neural Information Processing Systems, 2001.Markdown
[Williams and Zweck. "A Rotation and Translation Invariant Discrete Saliency Network." Neural Information Processing Systems, 2001.](https://mlanthology.org/neurips/2001/williams2001neurips-rotation/)BibTeX
@inproceedings{williams2001neurips-rotation,
title = {{A Rotation and Translation Invariant Discrete Saliency Network}},
author = {Williams, Lance R. and Zweck, John W.},
booktitle = {Neural Information Processing Systems},
year = {2001},
pages = {1319-1326},
url = {https://mlanthology.org/neurips/2001/williams2001neurips-rotation/}
}