FMP: Enhancing 3D Point Cloud Classification With Functional Multi-Head Pooling to Surpass PointNet

PointNet, the first deep learning framework for processing 3D point clouds, suffers from significant information loss during point cloud classification due to its Max pooling method, leading to decreased performance and accuracy when handling large-scale point clouds. In this paper, we propose an im...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.127931-127942
Main Authors: Jin, Zhan, Xu, Fan, Lu, Zhongyuan, Liu, Jin
Format: Article
Language:English
Subjects:
Accuracy
Classification
Controllability
Data mining
Datasets
Deep learning
Feature extraction
Feature recognition
FMP
functional
Functionals
Invariants
Minimax techniques
multi-head pooling
permutation invariant
Permutations
Point cloud compression
Three dimensional models
Three-dimensional displays
Trigonometric functions
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:PointNet, the first deep learning framework for processing 3D point clouds, suffers from significant information loss during point cloud classification due to its Max pooling method, leading to decreased performance and accuracy when handling large-scale point clouds. In this paper, we propose an improved method for PointNet classification accuracy-a Functional Multi-head Pooling encoding model. Based on the permutation-invariant functional concept, this model constructs richer multi-head invariant feature vectors, significantly enhancing recognition classification scores, and introducing a new model-Functional Multi-head Pooling (FMP)-capable of reducing overfitting. Due to the non-monotonicity, continuous differentiability, and controllable amplitude of functionals, we conducted experiments using cosine and sine trigonometric functions to replace the baseline Max method. The new approach also involves aggregating the results of the cosine and sine transformations, which allows for retaining more features during training compared to PointNet, thereby enhancing the training model's capabilities. Our three rounds of experiments on two datasets including ModelNet40 have proven the effectiveness of the functional approach. The new method can increase accuracy by up to 3.25% on the same datasets and significantly improving generalization capabilities.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3456107