papers AI Learner
The Github is limit! Click to go to the new site.

Supervized Segmentation with Graph-Structured Deep Metric Learning

2019-05-10
Loic Landrieu, Mohamed Boussaha

Abstract

We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promotes learning vertex embeddings which are homogeneous within desired segments, and have high contrast at their interface. Thus, computing a piecewise-constant approximation of such embeddings produces a graph-partition close to the objective segmentation. This loss is fully backpropagable, which allows us to learn vertex embeddings with deep learning algorithms. We evaluate our methods on a 3D point cloud oversegmentation task, defining a new state-of-the-art by a large margin. These results are based on the published work of Landrieu and Boussaha 2019.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.04014

PDF

http://arxiv.org/pdf/1905.04014


Similar Posts

Comments