Semantic Segmentation with Object Clique Potential
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.
Cite
Text
Qi et al. "Semantic Segmentation with Object Clique Potential." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.297Markdown
[Qi et al. "Semantic Segmentation with Object Clique Potential." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/qi2015iccv-semantic/) doi:10.1109/ICCV.2015.297BibTeX
@inproceedings{qi2015iccv-semantic,
title = {{Semantic Segmentation with Object Clique Potential}},
author = {Qi, Xiaojuan and Shi, Jianping and Liu, Shu and Liao, Renjie and Jia, Jiaya},
booktitle = {International Conference on Computer Vision},
year = {2015},
doi = {10.1109/ICCV.2015.297},
url = {https://mlanthology.org/iccv/2015/qi2015iccv-semantic/}
}