Semantic Instance Segmentation via Deep Metric Learning
This addresses instance segmentation for computer vision applications, but it is incremental as it builds on existing methods with a hybrid approach.
The paper tackles semantic instance segmentation by using a deep metric learning approach to compute pixel similarity and group them, achieving competitive results on the Pascal VOC benchmark.
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.