DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction

03/08/2022
by   Jiajun Fei, et al.
0

Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in simpler structures, their performance is poorer than the local aggregation ones like PointNet++ and Point Transformer. It remains an open problem whether there exists a global aggregation method with a simple structure, competitive performance, and even much fewer parameters. In this paper, we propose a novel global aggregation permutation-invariant network based on dual MLP dot-product, called DuMLP-Pin, which is capable of being employed to extract features for set inputs, including unordered or unstructured pixel, attribute, and point cloud data sets. We strictly prove that any permutation-invariant function implemented by DuMLP-Pin can be decomposed into two or more permutation-equivariant ones in a dot-product way as the cardinality of the given input set is greater than a threshold. We also show that the DuMLP-Pin can be viewed as Deep Sets with strong constraints under certain conditions. The performance of DuMLP-Pin is evaluated on several different tasks with diverse data sets. The experimental results demonstrate that our DuMLP-Pin achieves the best results on the two classification problems for pixel sets and attribute sets. On both the point cloud classification and the part segmentation, the accuracy of DuMLP-Pin is very close to the so-far best-performing local aggregation method with only a 1-2 number of required parameters is significantly reduced by more than 85 classification and 69 available on https://github.com/JaronTHU/DuMLP-Pin.

READ FULL TEXT

page 5

page 7

research
11/02/2020

Point Transformer

In this work, we present Point Transformer, a deep neural network that o...
research
06/23/2022

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets

Permutation invariant neural networks are a promising tool for making pr...
research
03/29/2021

SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data

Generative modeling of set-structured data, such as point clouds, requir...
research
08/31/2023

Decoupled Local Aggregation for Point Cloud Learning

The unstructured nature of point clouds demands that local aggregation b...
research
06/08/2023

Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification

Learning from set-structured data, such as point clouds, has gained sign...
research
09/10/2017

Classifying Unordered Feature Sets with Convolutional Deep Averaging Networks

Unordered feature sets are a nonstandard data structure that traditional...
research
12/12/2012

Learning with Scope, with Application to Information Extraction and Classification

In probabilistic approaches to classification and information extraction...

Please sign up or login with your details

Forgot password? Click here to reset