Fully Convolutional Instance-Aware Semantic Segmentation

Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji, Yichen Wei

CVPR 2017

doi:10.1109/CVPR.2017.472 /cvpr/2017/li2017cvpr-fully/

Abstract

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation and instance mask proposal. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The network architecture is highly integrated and efficient. It achieves state-of-the-art performance in both accuracy and efficiency. It wins the COCO 2016 segmentation competition by a large margin. Code would be released.

PDF CVPR Semantic Scholar

Cite

Text

Li et al. "Fully Convolutional Instance-Aware Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.472

Markdown

[Li et al. "Fully Convolutional Instance-Aware Semantic Segmentation." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/li2017cvpr-fully/) doi:10.1109/CVPR.2017.472

BibTeX

@inproceedings{li2017cvpr-fully,
  title     = {{Fully Convolutional Instance-Aware Semantic Segmentation}},
  author    = {Li, Yi and Qi, Haozhi and Dai, Jifeng and Ji, Xiangyang and Wei, Yichen},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.472},
  url       = {https://mlanthology.org/cvpr/2017/li2017cvpr-fully/}
}