A Self-Organizing Multiple-View Representation of 3D Objects
Abstract
We demonstrate the ability of a two-layer network of thresholded summation units to support representation of 3D objects in which several distinct 2D views are stored for ea.ch object. Using unsu(cid:173) pervised Hebbian relaxation, the network learned to recognize ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network ex(cid:173) hibited a substantial generalization capability. In simulated psy(cid:173) chophysical experiments, the network's behavior was qualitatively similar to that of human subjects.
Cite
Text
Weinshall et al. "A Self-Organizing Multiple-View Representation of 3D Objects." Neural Information Processing Systems, 1989.Markdown
[Weinshall et al. "A Self-Organizing Multiple-View Representation of 3D Objects." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/weinshall1989neurips-selforganizing/)BibTeX
@inproceedings{weinshall1989neurips-selforganizing,
title = {{A Self-Organizing Multiple-View Representation of 3D Objects}},
author = {Weinshall, Daphna and Edelman, Shimon and Bülthoff, Heinrich H.},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {274-281},
url = {https://mlanthology.org/neurips/1989/weinshall1989neurips-selforganizing/}
}