Learning to Parse Images

Abstract

We describe a class of probabilistic models that we call credibility networks. Using parse trees as internal representations of images, credibility networks are able to perform segmentation and recog(cid:173) nition simultaneously, removing the need for ad hoc segmentation heuristics. Promising results in the problem of segmenting hand(cid:173) written digits were obtained.

Cite

Text

Hinton et al. "Learning to Parse Images." Neural Information Processing Systems, 1999.

Markdown

[Hinton et al. "Learning to Parse Images." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/hinton1999neurips-learning/)

BibTeX

@inproceedings{hinton1999neurips-learning,
  title     = {{Learning to Parse Images}},
  author    = {Hinton, Geoffrey E. and Ghahramani, Zoubin and Teh, Yee Whye},
  booktitle = {Neural Information Processing Systems},
  year      = {1999},
  pages     = {463-469},
  url       = {https://mlanthology.org/neurips/1999/hinton1999neurips-learning/}
}