Litcius/Paper detail

Enrich Features for Few-Shot Point Cloud Classification

Hengxin Feng, Weifeng Liu, Yanjiang Wang, Baodi Liu

2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)11 citationsDOI

Abstract

Recently, many existing fully supervised methods for point cloud classification have strongly promoted the development of point cloud learning. However, these methods require a lot of labeled data as support, which is challenging to obtain. To alleviate this problem, we propose a novel few-shot point cloud classification method to classify new categories given a few labeled samples. Specifically, we apply the feature supplement module to enrich the geometric information of points and then aggregate multi-scale features through the channel-wise attention module while reducing the computational complexity. Finally, we introduce a classifier to classify the point cloud features under the few-shot learning setup to predict its label. We carry out experimental verification on the benchmark dataset and achieve state-of-the-art performance.

Topics & Concepts

Point cloudComputer scienceCloud computingClassifier (UML)Artificial intelligenceBenchmark (surveying)Machine learningPoint (geometry)Feature extractionContextual image classificationFeature (linguistics)Data miningPattern recognition (psychology)Image (mathematics)MathematicsOperating systemLinguisticsGeodesyPhilosophyGeographyGeometry3D Shape Modeling and Analysis3D Surveying and Cultural HeritageAdvanced Numerical Analysis Techniques