---
title: "General Purpose Models: Expectations About The Unexpected"
authors:
  - "Steven W. Zucker"
  - "Azriel Rosenfeld"
  - "Larry S. Davis"
doi: ""
url: "https://ijcai.org/proceedings/1975/113"
pdf: "https://ijcai.org/proceedings/1975/0113.pdf"
venue: "Proceedings of the Fourth International Joint Conference on Artificial Intelligence"
year: 1975
pages: "716-720"
track: "Visual Information Processing"
keywords:
---

# General Purpose Models: Expectations About The Unexpected

Steven W. Zucker, Azriel Rosenfeld, Larry S. Davis

*Proceedings of the Fourth International Joint Conference on Artificial Intelligence*, pages 716-720.

## Abstract

How can computer vision systems be designed to handle unfamiliar or unexpected sc~nes? Many of the current systems cope qu~te well with limited visual worlds, by mak~ng use of specialized knowledge about these worlds. But if we want to expand t~ese systems to handle a wide range of v7sual domains, it will not be enough to s~mply 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 ~eatures or regions or groups of these, ~n the absence of specific context.