Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation

Heesoo Myeong, Kyoung Mu Lee; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 3073-3080

Abstract


We propose a novel nonparametric approach for semantic segmentation using high-order semantic relations. Conventional context models mainly focus on learning pairwise relationships between objects. Pairwise relations, however, are not enough to represent high-level contextual knowledge within images. In this paper, we propose semantic relation transfer, a method to transfer high-order semantic relations of objects from annotated images to unlabeled images analogous to label transfer techniques where label information are transferred. We first define semantic tensors representing high-order relations of objects. Semantic relation transfer problem is then formulated as semi-supervised learning using a quadratic objective function of the semantic tensors. By exploiting low-rank property of the semantic tensors and employing Kronecker sum similarity, an efficient approximation algorithm is developed. Based on the predicted high-order semantic relations, we reason semantic segmentation and evaluate the performance on several challenging datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Myeong_2013_CVPR,
author = {Myeong, Heesoo and Mu Lee, Kyoung},
title = {Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}