Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach

01/18/2021
by   Xian Shi, et al.
15

Semantic segmentation of 3D point clouds relies on training deep models with a large amount of labeled data. However, labeling 3D point clouds is expensive, thus smart approach towards data annotation, a.k.a. active learning is essential to label-efficient point cloud segmentation. In this work, we first propose a more realistic annotation counting scheme so that a fair benchmark is possible. To better exploit labeling budget, we adopt a super-point based active learning strategy where we make use of manifold defined on the point cloud geometry. We further propose active learning strategy to encourage shape level diversity and local spatial consistency constraint. Experiments on two benchmark datasets demonstrate the efficacy of our proposed active learning strategy for label-efficient semantic segmentation of point clouds. Notably, we achieve significant improvement at all levels of annotation budgets and outperform the state-of-the-art methods under the same level of annotation cost.

READ FULL TEXT

page 6

page 11

page 12

page 13

page 14

page 15

research
02/25/2022

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning

The expensive annotation cost is notoriously known as a main constraint ...
research
04/23/2023

You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation

We propose SeedAL, a method to seed active learning for efficient annota...
research
11/26/2019

ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation

We propose ViewAL, a novel active learning strategy for semantic segment...
research
04/13/2021

All you need are a few pixels: semantic segmentation with PixelPick

A central challenge for the task of semantic segmentation is the prohibi...
research
06/13/2023

Low-Resource White-Box Semantic Segmentation of Supporting Towers on 3D Point Clouds via Signature Shape Identification

Research in 3D semantic segmentation has been increasing performance met...
research
02/16/2023

Navya3DSeg – Navya 3D Semantic Segmentation Dataset split generation for autonomous vehicles

Autonomous driving (AD) perception today relies heavily on deep learning...
research
04/28/2020

Active Learning for Coreference Resolution using Discrete Annotation

We improve upon pairwise annotation for active learning in coreference r...

Please sign up or login with your details

Forgot password? Click here to reset