<title>Invariance problem for hierarchical neural networks</title>
Lists
Only you see this
Abstract
Hierarchically organized neural networks are well suited for visual information processing. These models offer a way to cope with the complexity of vision. We identify strong relationships between hierarchical neural networks and image pyramids. However, we also show that if one has the freedom to choose the input patterns, these neural networks are not intrinsically shift invariant. In order to circumvent this problem we propose a new neural network architecture called `Neural Networks in Image Pyramids.' We use hierarchical neural networks with local connectivity (image pyramids) as stem networks. These networks generate hypotheses about the expected image content. These hypotheses are checked by small neural network modules which are used selectively on parts of the image. We give an example demonstrating the solution of the shift variance problem. Finally, we outline directions of further research.
BibTeX
@inproceedings{bischof1992lt,
author = {Horst Bischof and Axel Pinz},
title = {{\<title\>Invariance problem for hierarchical neural networks\</title\>}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {1992},
doi = {10.1117/12.130823},
}Loading related content...