paper-with-me

Papers

Supervized Segmentation with Graph-Structured Deep Metric Learning

2019-05-10 · Loic Landrieu, Mohamed Boussaha

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.

📄 PDF Abstract BibTeX arXiv:1905.04014

Code (1)

loicland/superpoint_graph 공식 구현 pytorch

Tasks

Metric LearningSegmentation

Similar Papers 제목 키워드 기반

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

2019-04-03 · CVPR 2019 6 · Loic Landrieu, Mohamed Boussaha

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border…

Semantic Segmentation

Segmentation non supervis\'ee : le cas du mandarin (Unsupervized Word Segmentation) [in French]

2012-06-01 · JEPTALNRECITAL 2012 6 · Pierre Magistry
Chinese Word SegmentationSegmentation

Unsupervized Word Segmentation: the Case for Mandarin Chinese

2012-07-01 · ACL 2012 7 · Pierre Magistry, Beno{\^\i}t Sagot

Design of an Input Method for Taiwanese Hokkien using Unsupervized Word Segmentation for Language Modeling

2016-10-01 · ROCLINGIJCLCLP 2016 10 · Pierre Magistry
Language ModelingLanguage Modelling

Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation

2019-10-01 · ICCV 2019 10 · Chi Zhang, Guosheng Lin, Fayao Liu, Jiushuang Guo 외

One-shot image segmentation aims to undertake the segmentation task of a novel class with only one training image available. The difficulty lies in that image segmentation has structured data representations, which yield…

Few-Shot Semantic SegmentationGraph AttentionImage SegmentationSegmentation+1