General Purpose Models: Expectations About the Unexpected
Abstract
How can computer vision systems be designed to handle unfamiliar or unexpected scenes? Many of the current systems cope quite well with limited visual worlds, by making use of specialized knowledge about these worlds- But if we want to expand these systems to handle a wide range of visual domains, it will not be enough to simply employ a large number of specialized models. It will also be important to make use of what might be called "general-purpose models. " Such models can be used to suggest reasonable descriptions for a given scene, e.g., in terms of
Cite
Text
Zucker et al. "General Purpose Models: Expectations About the Unexpected." International Joint Conference on Artificial Intelligence, 1975.Markdown
[Zucker et al. "General Purpose Models: Expectations About the Unexpected." International Joint Conference on Artificial Intelligence, 1975.](https://mlanthology.org/ijcai/1975/zucker1975ijcai-general/)BibTeX
@inproceedings{zucker1975ijcai-general,
title = {{General Purpose Models: Expectations About the Unexpected}},
author = {Zucker, Steven W. and Rosenfeld, Azriel and Davis, Larry S.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1975},
pages = {716-721},
url = {https://mlanthology.org/ijcai/1975/zucker1975ijcai-general/}
}