Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation

by   Yangheng Zhao, et al.
University of Maryland
Shanghai Jiao Tong University
Virginia Polytechnic Institute and State University

3D point cloud semantic segmentation is one of the fundamental tasks for 3D scene understanding and has been widely used in the metaverse applications. Many recent 3D semantic segmentation methods learn a single prototype (classifier weights) for each semantic class, and classify 3D points according to their nearest prototype. However, learning only one prototype for each class limits the model's ability to describe the high variance patterns within a class. Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class. With the powerful capability of vision transformer, we design a Number-Adaptive Prototype Learning (NAPL) model for point cloud semantic segmentation. To train our NAPL model, we propose a simple yet effective prototype dropout training strategy, which enables our model to adaptively produce prototypes for each class. The experimental results on SemanticKITTI dataset demonstrate that our method achieves 2.3 classification paradigm.


page 1

page 2

page 3

page 4


Point Cloud Semantic Segmentation

Semantic segmentation is an important and well-known task in the field o...

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

Few-shot segmentation of point cloud remains a challenging task, as ther...

Discriminative Probabilistic Prototype Learning

In this paper we propose a simple yet powerful method for learning repre...

Learning from Mistakes: Self-Regularizing Hierarchical Semantic Representations in Point Cloud Segmentation

Recent advances in autonomous robotic technologies have highlighted the ...

Prototype Guided Network for Anomaly Segmentation

Semantic segmentation methods can not directly identify abnormal objects...

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation

Prototype-based classification is a classical method in machine learning...

Rethinking Semantic Segmentation: A Prototype View

Prevalent semantic segmentation solutions, despite their different netwo...

Please sign up or login with your details

Forgot password? Click here to reset