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

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.