Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context

CVPR 2013

doi:10.1109/CVPR.2013.405 /cvpr/2013/singh2013cvpr-nonparametric/

Abstract

This paper presents a nonparametric approach to semantic parsing using small patches and simple gradient, color and location features. We learn the relevance of individual feature channels at test time using a locally adaptive distance metric. To further improve the accuracy of the nonparametric approach, we examine the importance of the retrieval set used to compute the nearest neighbours using a novel semantic descriptor to retrieve better candidates. The approach is validated by experiments on several datasets used for semantic parsing demonstrating the superiority of the method compared to the state of art approaches.

PDF CVPR Semantic Scholar

Cite

Text

Singh and Kosecka. "Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.405

Markdown

[Singh and Kosecka. "Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/singh2013cvpr-nonparametric/) doi:10.1109/CVPR.2013.405

BibTeX

@inproceedings{singh2013cvpr-nonparametric,
  title     = {{Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context}},
  author    = {Singh, Gautam and Kosecka, Jana},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.405},
  url       = {https://mlanthology.org/cvpr/2013/singh2013cvpr-nonparametric/}
}