Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context

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 app...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 3151 - 3157
Main Authors Singh, Gautam, Kosecka, Jana
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Accuracy
Context
feature relevance
Image color analysis
Labeling
Measurement
scene understanding
semantic segmentation
Semantics
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.405