ML Anthology

Explicit Shape Encoding for Real-Time Instance Segmentation

Wenqiang Xu, Haiyang Wang, Fubo Qi, Cewu Lu
ICCV 2019
doi:10.1109/ICCV.2019.00527 /iccv/2019/xu2019iccv-explicit/

Abstract

In this paper, we propose a novel top-down instance segmentation framework based on explicit shape encoding, named ESE-Seg. It largely reduces the computational consumption of the instance segmentation by explicitly decoding the multiple object shapes with tensor operations, thus performs the instance segmentation at almost the same speed as the object detection. ESE-Seg is based on a novel shape signature Inner-center Radius (IR), Chebyshev polynomial fitting and the strong modern object detectors. ESE-Seg with YOLOv3 outperforms the Mask R-CNN on Pascal VOC 2012 at mAP^[email protected] while 7 times faster.

PDF ICCV Semantic Scholar

Cite

Text

Xu et al. "Explicit Shape Encoding for Real-Time Instance Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00527

Markdown

[Xu et al. "Explicit Shape Encoding for Real-Time Instance Segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/xu2019iccv-explicit/) doi:10.1109/ICCV.2019.00527

BibTeX

@inproceedings{xu2019iccv-explicit,
  title     = {{Explicit Shape Encoding for Real-Time Instance Segmentation}},
  author    = {Xu, Wenqiang and Wang, Haiyang and Qi, Fubo and Lu, Cewu},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year      = {2019},
  doi       = {10.1109/ICCV.2019.00527},
  url       = {https://mlanthology.org/iccv/2019/xu2019iccv-explicit/}
}