Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections

Abstract

Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery models from statistical text analysis; and (ii) that visual object classes can be used to assess the accuracy of a segmentation. To tie these ideas together we compute multiple segmentations of each image and then: (i) learn the object classes; and (ii) choose the correct segmentations. We demonstrate that such an algorithm succeeds in automatically discovering many familiar objects in a variety of image datasets, including those from Caltech, MSRC and LabelMe.

Cite

Text

Russell et al. "Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.326

Markdown

[Russell et al. "Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/russell2006cvpr-using/) doi:10.1109/CVPR.2006.326

BibTeX

@inproceedings{russell2006cvpr-using,
  title     = {{Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections}},
  author    = {Russell, Bryan C. and Freeman, William T. and Efros, Alexei A. and Sivic, Josef and Zisserman, Andrew},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1605-1614},
  doi       = {10.1109/CVPR.2006.326},
  url       = {https://mlanthology.org/cvpr/2006/russell2006cvpr-using/}
}