Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data

Liu Yang, Rong Jin, Caroline Pantofaru, and Rahul Sukthankar
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, July, 2007.


Download
  • Adobe portable document format (pdf) (191KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
A popular approach to problems in image classification is to represent the image as a bag of visual words and then employ a classifier to categorize the image. Unfortunately, a significant shortcoming of this approach is that the clustering and classification are disconnected. Since the clustering into visual words is unsupervised, the representation does not necessarily capture the aspects of the data that are most useful for classification. More seriously, the semantic relationship between clusters is lost, causing the overall classification performance to suffer.

We introduce ?iscriminative cluster refinement?(DCR), a method that explicitly models the pairwise relationships between different visual words by exploiting their co-occurrence information. The assigned class labels are used to identify the co-occurrence patterns that are most informative for object classification. DCR employs a maximum-margin approach to generate an optimal kernel matrix for classification. One important benefit of DCR is that it integrates smoothly into existing bag-of-words information retrieval systems by employing the set of visual words generated by any clustering method. While DCR could improve a broad class of information retrieval systems, this paper focuses on object category recognition. We present a direct comparison with a state-of-the art method on the PASCAL 2006 database and show that cluster refinement results in a significant improvement in classification accuracy given a small number of training examples.


Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Number of pages: 8

Text Reference
Liu Yang, Rong Jin, Caroline Pantofaru, and Rahul Sukthankar, "Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, July, 2007.

BibTeX Reference
@inproceedings{Pantofaru_2007_5790,
   author = "Liu Yang and Rong Jin and Caroline Pantofaru and Rahul Sukthankar",
   title = "Discriminative Cluster Refinement: Improving Object Category Recognition Given Limited Training Data",
   booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition",
   month = "July",
   year = "2007",
}