We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together. Our similarity metric is based on a deep, fully convolutional embedding model. Our grouping method is based on selecting all points that are sufficiently similar to a set of "seed points", chosen from a deep, fully convolutional scoring model. We show competitive results on the Pascal VOC instance segmentation benchmark.
@article{arxiv.1703.10277,
title = {Semantic Instance Segmentation via Deep Metric Learning},
author = {Alireza Fathi and Zbigniew Wojna and Vivek Rathod and Peng Wang and Hyun Oh Song and Sergio Guadarrama and Kevin P. Murphy},
journal= {arXiv preprint arXiv:1703.10277},
year = {2017}
}