11-09
Uncertainty in Natural Image Segmentation

We explore nonparametric Bayesian statistical models for image partitions which coherently model uncertainty in the size, shape, and structure of human image interpretations. Examining a large set of manually segmented scenes, we show that object frequencies and segment sizes both follow power law distributions, which are well modeled by the Pitman-Yor (PY) process. This generalization of the Dirichlet process leads to segmentation algorithms which automatically adapt their resolution to each image. Generalizing previous applications of PY priors, we use non-Markov Gaussian processes (GPs) to infer spatially contiguous segments which respect image boundaries. We show how GP covariance functions can be calibrated to accurately match the statistics of human segmentations, and that robust posterior inference is possible via a variational method, expectation propagation. The resulting method produces highly accurate segmentations of complex scenes, and hypothesizes multiple image partitions to capture the variability inherent in human scene interpretations.
Date and Time
Wednesday November 9, 2011 4:30pm - 5:30pm
Location
Computer Science Small Auditorium (Room 105)
Host
David Blei

Contributions to and/or sponsorship of any event does not constitute departmental or institutional endorsement of the specific program, speakers or views presented.

CS Talks Mailing List