Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud Classification

01/27/2022
by   Feng Yang, et al.
0

Learning a powerful representation from point clouds is a fundamental and challenging problem in the field of computer vision. Different from images where RGB pixels are stored in the regular grid, for point clouds, the underlying semantic and structural information of point clouds is the spatial layout of the points. Moreover, the properties of challenging in-context and background noise pose more challenges to point cloud analysis. One assumption is that the poor performance of the classification model can be attributed to the indistinguishable embedding feature that impedes the search for the optimal classifier. This work offers a new strategy for learning powerful representations via a contrastive learning approach that can be embedded into any point cloud classification network. First, we propose a supervised contrastive classification method to implement embedding feature distribution refinement by improving the intra-class compactness and inter-class separability. Second, to solve the confusion problem caused by small inter-class compactness and inter-class separability. Second, to solve the confusion problem caused by small inter-class variations between some similar-looking categories, we propose a confusion-prone class mining strategy to alleviate the confusion effect. Finally, considering that outliers of the sample clusters in the embedding space may cause performance degradation, we design an entropy-aware attention module with information entropy theory to identify the outlier cases and the unstable samples by measuring the uncertainty of predicted probability. The results of extensive experiments demonstrate that our method outperforms the state-of-the-art approaches by achieving 82.9 performance gains up to 2.9

READ FULL TEXT

page 1

page 11

page 14

research
07/27/2023

Clustering based Point Cloud Representation Learning for 3D Analysis

Point cloud analysis (such as 3D segmentation and detection) is a challe...
research
12/09/2021

SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

Pre-training has become a standard paradigm in many computer vision task...
research
10/11/2022

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

Due to the few annotated labels of 3D point clouds, how to learn discrim...
research
07/07/2021

GA-NET: Global Attention Network for Point Cloud Semantic Segmentation

How to learn long-range dependencies from 3D point clouds is a challengi...
research
02/22/2023

S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classification

Many point cloud classification methods are developed under the assumpti...
research
07/19/2021

Unsupervised Embedding Learning from Uncertainty Momentum Modeling

Existing popular unsupervised embedding learning methods focus on enhanc...
research
09/14/2022

I2CR: Improving Noise Robustness on Keyword Spotting Using Inter-Intra Contrastive Regularization

Noise robustness in keyword spotting remains a challenge as many models ...

Please sign up or login with your details

Forgot password? Click here to reset