Unsupervised Classification and Part Localization by Consistency Amplification

@inproceedings{Karlinsky2008UnsupervisedCA,
  title={Unsupervised Classification and Part Localization by Consistency Amplification},
  author={Leonid Karlinsky and Michael Dinerstein and Dan Levi and Shimon Ullman},
  booktitle={ECCV},
  year={2008}
}
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, some of which contain an object of an unknown category, with unknown location and unknown size relative to the background, the method automatically identifies the images that contain the objects, localizes them and their parts, and reliably learns their appearance and geometry for subsequent classification. Current… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 17 extracted citations

Combined model for detecting , localizing , interpreting and recognizing faces

michael. dinerstein, D. Franklin Levi, shimon. ullman
2008
View 10 Excerpts
Highly Influenced

Planogram Compliance Checking Using Recurring Patterns

2015 IEEE International Symposium on Multimedia (ISM) • 2015
View 1 Excerpt

Fusing visual and range imaging for object class recognition

2011 International Conference on Computer Vision • 2011
View 1 Excerpt

Unsupervised Image Categorization by Hypergraph Partition

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2011
View 1 Excerpt

Detecting and sketching the common

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition • 2010
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Discovering hierarchical taxonomy of categories and shared subcategories in images

N. Ahuja, S. Todorovic
ICCV • 2007
View 4 Excerpts
Highly Influenced

OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning

International Journal of Computer Vision • 2007
View 6 Excerpts
Highly Influenced

Unsupervised Image Categorization and Object Localization using Topic Models and Correspondences between Images

2007 IEEE 11th International Conference on Computer Vision • 2007
View 10 Excerpts
Highly Influenced

Weighted Substructure Mining for Image Analysis

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 6 Excerpts
Highly Influenced

Semantic-Shift for Unsupervised Object Detection

2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06) • 2006
View 8 Excerpts
Highly Influenced

Towards Unsupervised Discovery of Visual Categories

DAGM-Symposium • 2006
View 4 Excerpts
Highly Influenced

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

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) • 2006
View 5 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…