Supervized Segmentation with Graph-Structured Deep Metric Learning

05/10/2019
by   Loic Landrieu, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 8

page 11

04/03/2019

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

We propose a new supervized learning framework for oversegmenting 3D poi...
06/25/2020

Adaptive additive classification-based loss for deep metric learning

Recent works have shown that deep metric learning algorithms can benefit...
06/29/2021

Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography

Most existing deep learning-based frameworks for image segmentation assu...
05/15/2019

Embeddings and Representation Learning for Structured Data

Performing machine learning on structured data is complicated by the fac...
01/31/2019

Learning Metric Graphs for Neuron Segmentation In Electron Microscopy Images

In the deep metric learning approach to image segmentation, a convolutio...
03/06/2013

Large-Margin Metric Learning for Partitioning Problems

In this paper, we consider unsupervised partitioning problems, such as c...
07/23/2018

Deep Learning from Label Proportions for Emphysema Quantification

We propose an end-to-end deep learning method that learns to estimate em...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.