SGN: Sequential Grouping Networks for Instance Segmentation

Shu Liu, Jiaya Jia, Sanja Fidler, Raquel Urtasun; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3496-3504

Abstract


In this paper, we propose Sequential Grouping Networks (SGN) to tackle the problem of object instance segmentation. SGNs employ a sequence of neural networks, each solving a sub-grouping problem of increasing semantic complexity in order to gradually compose objects out of pixels. In particular, the first network aims to group pixels along each image row and column by predicting horizontal and vertical object breakpoints. These breakpoints are then used to create line segments. By exploiting two-directional information, the second network groups horizontal and vertical lines into connected components. Finally, the third network groups the connected components into object instances. Our experiments show that our SGN significantly outperforms state-of-the-art approaches in both, the Cityscapes dataset as well as PASCAL VOC.

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2017_ICCV,
author = {Liu, Shu and Jia, Jiaya and Fidler, Sanja and Urtasun, Raquel},
title = {SGN: Sequential Grouping Networks for Instance Segmentation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}