Supervized Segmentation with Graph-Structured Deep Metric Learning
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.
Code (1)
Tasks
Metric LearningSegmentationSimilar Papers 제목 키워드 기반
Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning
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 SegmentationSegmentation non supervis\'ee : le cas du mandarin (Unsupervized Word Segmentation) [in French]
Unsupervized Word Segmentation: the Case for Mandarin Chinese
Design of an Input Method for Taiwanese Hokkien using Unsupervized Word Segmentation for Language Modeling
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation
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