Affinity Derivation and Graph Merge for Instance Segmentation
Abstract
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.
Cite
Text
Liu et al. "Affinity Derivation and Graph Merge for Instance Segmentation." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01219-9_42Markdown
[Liu et al. "Affinity Derivation and Graph Merge for Instance Segmentation." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/liu2018eccv-affinity/) doi:10.1007/978-3-030-01219-9_42BibTeX
@inproceedings{liu2018eccv-affinity,
title = {{Affinity Derivation and Graph Merge for Instance Segmentation}},
author = {Liu, Yiding and Yang, Siyu and Li, Bin and Zhou, Wengang and Xu, Jizheng and Li, Houqiang and Lu, Yan},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01219-9_42},
url = {https://mlanthology.org/eccv/2018/liu2018eccv-affinity/}
}