What Makes a Patch Distinct?

Ran Margolin, Ayellet Tal, Lihi Zelnik-Manor

CVPR 2013

doi:10.1109/CVPR.2013.151 /cvpr/2013/margolin2013cvpr-makes/

Abstract

What makes an object salient? Most previous work assert that distinctness is the dominating factor. The difference between the various algorithms is in the way they compute distinctness. Some focus on the patterns, others on the colors, and several add high-level cues and priors. We propose a simple, yet powerful, algorithm that integrates these three factors. Our key contribution is a novel and fast approach to compute pattern distinctness. We rely on the inner statistics of the patches in the image for identifying unique patterns. We provide an extensive evaluation and show that our approach outperforms all state-of-the-art methods on the five most commonly-used datasets.

PDF CVPR Semantic Scholar

Cite

Text

Margolin et al. "What Makes a Patch Distinct?." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.151

Markdown

[Margolin et al. "What Makes a Patch Distinct?." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/margolin2013cvpr-makes/) doi:10.1109/CVPR.2013.151

BibTeX

@inproceedings{margolin2013cvpr-makes,
  title     = {{What Makes a Patch Distinct?}},
  author    = {Margolin, Ran and Tal, Ayellet and Zelnik-Manor, Lihi},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.151},
  url       = {https://mlanthology.org/cvpr/2013/margolin2013cvpr-makes/}
}