Enrich Features for Few-Shot Point Cloud Classification
Hengxin Feng, Weifeng Liu, Yanjiang Wang, Baodi Liu
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.