PolyTransform: Deep Polygon Transformer for Instance Segmentation
Abstract
In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In particular, we first exploit a segmentation network to generate instance masks. We then convert the masks into a set of polygons that are then fed to a deforming network that transforms the polygons such that they better fit the object boundaries. Our experiments on the challenging Cityscapes dataset show that our PolyTransform significantly improves the performance of the backbone instance segmentation network and ranks 1st on the Cityscapes test-set leaderboard. We also show impressive gains in the interactive annotation setting.
Cite
Text
Liang et al. "PolyTransform: Deep Polygon Transformer for Instance Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00915Markdown
[Liang et al. "PolyTransform: Deep Polygon Transformer for Instance Segmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/liang2020cvpr-polytransform/) doi:10.1109/CVPR42600.2020.00915BibTeX
@inproceedings{liang2020cvpr-polytransform,
title = {{PolyTransform: Deep Polygon Transformer for Instance Segmentation}},
author = {Liang, Justin and Homayounfar, Namdar and Ma, Wei-Chiu and Xiong, Yuwen and Hu, Rui and Urtasun, Raquel},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.00915},
url = {https://mlanthology.org/cvpr/2020/liang2020cvpr-polytransform/}
}