Learning Localized Perceptual Similarity Metrics for Interactive Categorization

Catherine Wah, Subhransu Maji, Serge J. Belongie

WACV 2015 pp. 502-509

doi:10.1109/WACV.2015.73 /wacv/2015/wah2015wacv-learning/

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.

PDF WACV Semantic Scholar

Cite

Text

Wah et al. "Learning Localized Perceptual Similarity Metrics for Interactive Categorization." IEEE/CVF Winter Conference on Applications of Computer Vision, 2015. doi:10.1109/WACV.2015.73

Markdown

[Wah et al. "Learning Localized Perceptual Similarity Metrics for Interactive Categorization." IEEE/CVF Winter Conference on Applications of Computer Vision, 2015.](https://mlanthology.org/wacv/2015/wah2015wacv-learning/) doi:10.1109/WACV.2015.73

BibTeX

@inproceedings{wah2015wacv-learning,
  title     = {{Learning Localized Perceptual Similarity Metrics for Interactive Categorization}},
  author    = {Wah, Catherine and Maji, Subhransu and Belongie, Serge J.},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2015},
  pages     = {502-509},
  doi       = {10.1109/WACV.2015.73},
  url       = {https://mlanthology.org/wacv/2015/wah2015wacv-learning/}
}