Header logo is

Unsupervised Object Discovery: A Comparison




The goal of this paper is to evaluate and compare models and methods for learning to recognize basic entities in images in an unsupervised setting. In other words, we want to discover the objects present in the images by analyzing unlabeled data and searching for re-occurring patterns. We experiment with various baseline methods, methods based on latent variable models, as well as spectral clustering methods. The results are presented and compared both on subsets of Caltech256 and MSRC2, data sets that are larger and more challenging and that include more object classes than what has previously been reported in the literature. A rigorous framework for evaluating unsupervised object discovery methods is proposed.

Author(s): Tuytelaars, T. and Lampert, CH. and Blaschko, MB. and Buntine, W.
Journal: International Journal of Computer Vision
Volume: 88
Number (issue): 2
Pages: 284-302
Year: 2010
Month: June
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1007/s11263-009-0271-8
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Unsupervised Object Discovery: A Comparison},
  author = {Tuytelaars, T. and Lampert, CH. and Blaschko, MB. and Buntine, W.},
  journal = {International Journal of Computer Vision},
  volume = {88},
  number = {2},
  pages = {284-302},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = jun,
  year = {2010},
  month_numeric = {6}