Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation

Autor:	Max Welling, Andrew E. Gelfand, Charless C. Fowlkes, Yutian Chen
Rok vydání:	2011
Předmět:	Contextual image classification Discriminative model business.industry Piecewise Boundary (topology) Pattern recognition Pairwise comparison Graph theory Image segmentation Artificial intelligence business Data modeling Mathematics
Zdroj:	ICCV
DOI:	10.1109/iccv.2011.6126553
Popis:	We present a new method to combine possibly inconsistent locally (piecewise) trained conditional models p(y α ∣x α ) into pseudo-samples from a global model. Our method does not require training of a CRF, but instead generates samples by iterating forward a weakly chaotic dynamical system. The new method is illustrated on image segmentation tasks where classifiers based on local appearance cues are combined with pairwise boundary cues.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fc6d0f220a04b64358b216b9985834ec https://doi.org/10.1109/iccv.2011.6126553 Zobrazit plný text záznamu