Citation
F. Wang, Q. Huang, M. Ovsjanikov, L. Guibas. "Unsupervised Multi-Class Joint Image Segmentation". EEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

Abstract
Joint segmentation of image sets is a challenging problem, especially when there are multiple objects with variable appearance shared among the images in the collection and the set of objects present in each particular image is itself varying and unknown. In this paper, we present a novel method to jointly segment a set of images containing objects from multiple classes. We first establish consistent functional maps across the input images, and introduce a formulation that explicitly models partial similarity across images instead of global consistency. Given the optimized maps between pairs of images, multiple groups of consistent segmentation functions are found such that they align with segmentation cues in the images, agree with the functional maps, and are mutually exclusive. The proposed fully unsupervised approach exhibits a significant improvement over the state-of-the-art methods, as shown on the co- segmentation data sets MSRC, Flickr, and PASCAL.

Electronic downloads

• whog-umjis-14.pdf · application/pdf · 10301 kbytes

• HTML

  F. Wang, Q. Huang, M. Ovsjanikov, L. Guibas. <a
  href="http://robotics.eecs.berkeley.edu/pubs/17.html"
  >Unsupervised Multi-Class Joint Image
  Segmentation</a>, EEE Conference on Computer Vision
  and Pattern Recognition (CVPR), 2014.

• Plain text

  F. Wang, Q. Huang, M. Ovsjanikov, L. Guibas.
  "Unsupervised Multi-Class Joint Image
  Segmentation". EEE Conference on Computer Vision and
  Pattern Recognition (CVPR), 2014.

• BibTeX

  @inproceedings{WangHuangOvsjanikovGuibas14_UnsupervisedMultiClassJointImageSegmentation,
      author = {F. Wang and Q. Huang and M. Ovsjanikov and L.
                Guibas},
      title = {Unsupervised Multi-Class Joint Image Segmentation},
      booktitle = {EEE Conference on Computer Vision and Pattern
                Recognition (CVPR)},
      year = {2014},
      abstract = {Joint segmentation of image sets is a challenging
                problem, especially when there are multiple
                objects with variable appearance shared among the
                images in the collection and the set of objects
                present in each particular image is itself varying
                and unknown. In this paper, we present a novel
                method to jointly segment a set of images
                containing objects from multiple classes. We first
                establish consistent functional maps across the
                input images, and introduce a formulation that
                explicitly models partial similarity across images
                instead of global consistency. Given the optimized
                maps between pairs of images, multiple groups of
                consistent segmentation functions are found such
                that they align with segmentation cues in the
                images, agree with the functional maps, and are
                mutually exclusive. The proposed fully
                unsupervised approach exhibits a significant
                improvement over the state-of-the-art methods, as
                shown on the co- segmentation data sets MSRC,
                Flickr, and PASCAL.},
      URL = {http://robotics.eecs.berkeley.edu/pubs/17.html}
  }
  

Posted by Ehsan Elhamifar on 7 Jun 2014.
Groups: ehumans
For additional information, see the Publications FAQ or contact webmaster at robotics eecs berkeley edu.