Integrating Parametric and Non-Parametric Models For Scene Labeling

Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, Lifan Zhao; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 4249-4258

Abstract


We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification. As visually similar pixels are indistinguishable from local context, we alleviate such ambiguity by putting a global scene constraint. We estimate the global potential in a non-parametric framework. Furthermore, a large margin based CNN metric learning method is proposed for better global potential estimation. The final pixel class prediction is performed by integrating local and global beliefs. Even without any post-processing, we achieve state-of-the-art on SiftFlow and competitive results on Stanford Background benchmark.

Related Material


[pdf]
[bibtex]
@InProceedings{Shuai_2015_CVPR,
author = {Shuai, Bing and Wang, Gang and Zuo, Zhen and Wang, Bing and Zhao, Lifan},
title = {Integrating Parametric and Non-Parametric Models For Scene Labeling},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}