Managing Uncertainty in Cue Combination
Abstract
We develop a hierarchical generative model to study cue combi(cid:173) nation. The model maps a global shape parameter to local cue(cid:173) specific parameters, which in tum generate an intensity image. Inferring shape from images is achieved by inverting this model. Inference produces a probability distribution at each level; using distributions rather than a single value of underlying variables at each stage preserves information about the validity of each local cue for the given image. This allows the model, unlike standard combination models, to adaptively weight each cue based on gen(cid:173) eral cue reliability and specific image context. We describe the results of a cue combination psychophysics experiment we con(cid:173) ducted that allows a direct comparison with the model. The model provides a good fit to our data and a natural account for some in(cid:173) teresting aspects of cue combination.
Cite
Text
Yang and Zemel. "Managing Uncertainty in Cue Combination." Neural Information Processing Systems, 1999.Markdown
[Yang and Zemel. "Managing Uncertainty in Cue Combination." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/yang1999neurips-managing/)BibTeX
@inproceedings{yang1999neurips-managing,
title = {{Managing Uncertainty in Cue Combination}},
author = {Yang, Zhiyong and Zemel, Richard S.},
booktitle = {Neural Information Processing Systems},
year = {1999},
pages = {869-878},
url = {https://mlanthology.org/neurips/1999/yang1999neurips-managing/}
}