Learning Localized Perceptual Similarity Metrics for Interactive Categorization

Catherine Wah, Subhransu Maji, Serge J. Belongie

Abstract

Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.
BibTeX
@inproceedings{wah2015learning,
  author = {Catherine Wah and Subhransu Maji and Serge J. Belongie},
  title = {{Learning Localized Perceptual Similarity Metrics for Interactive Categorization}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2015},
  doi = {10.1109/wacv.2015.73},
}

Loading related content...

Figure