Recognition by Association via Learning Per-exemplar Distances

Tomasz Malisiewicz and Alexei A. Efros
Proc. Computer Vision and Pattern Recognition (CVPR), July, 2008.


Download
  • Adobe portable document format (pdf) (8MB)
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
We pose the recognition problem as data association. In this setting, a novel object is explained solely in terms of a small set of exemplar objects to which it is visually similar. Inspired by the work of Frome et al., we learn separate distance functions for each exemplar; however, our distances are interpretable on an absolute scale and can be thresholded to detect the presence of an object. Our exemplars are represented as image regions and the learned distances capture the relative importance of shape, color, texture, and position features for that region. We use the distance functions to detect and segment objects in novel images by associating the bottom-up segments obtained from multiple image segmentations with the exemplar regions. We evaluate the detection and segmentation performance of our algorithm on real-world outdoor scenes from the LabelMe dataset and also show some promising qualitative image parsing results.

Keywords
computer vision, object recognition

Notes
Sponsor: NSF

Text Reference
Tomasz Malisiewicz and Alexei A. Efros, "Recognition by Association via Learning Per-exemplar Distances," Proc. Computer Vision and Pattern Recognition (CVPR), July, 2008.

BibTeX Reference
@inproceedings{Malisiewicz_2008_6065,
   author = "Tomasz Malisiewicz and Alexei A. Efros",
   title = "Recognition by Association via Learning Per-exemplar Distances",
   booktitle = "Proc. Computer Vision and Pattern Recognition (CVPR)",
   month = "July",
   year = "2008",
}