Semantic Segmentation With Object Clique Potential

Xiaojuan Qi, Jianping Shi, Shu Liu, Renjie Liao, Jiaya Jia; The IEEE International Conference on Computer Vision (ICCV), 2015, pp. 2587-2595

Abstract


In this paper, we propose an object clique potential for semantic segmentation. Our object clique potential addresses the misclassified object-part issues arising in solutions based on fully-connected networks. Our object clique set, compared to that yielded from segment-proposal-based approaches, is with a significantly small size, making our method consume notably less computation. Regarding system design and model formation, our object clique potential can be regarded as a functionally complement to local-appearance-based CRF models and works in synergy with these effective approaches for further performance improvement. Extensive experiments verify our method.

Related Material


[pdf]
[bibtex]
@InProceedings{Qi_2015_ICCV,
author = {Qi, Xiaojuan and Shi, Jianping and Liu, Shu and Liao, Renjie and Jia, Jiaya},
title = {Semantic Segmentation With Object Clique Potential},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}