3D-model ShapeNet Core Classification using Meta-Semantic Learning
This addresses the need for efficient 3D model recognition in applications like autonomous driving, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of computationally expensive 3D point cloud classification by proposing Meta-Semantic Learning (Meta-SeL), which leverages semantic dimensions and part-segmentation labels to achieve competitive performance with state-of-the-art methods while being efficient and resilient to noise.
Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point cloud segmentation, object detection, and classification. These methods, however, often require a considerable number of model parameters and are computationally expensive. We study a semantic dimension of given 3D data points and propose an efficient method called Meta-Semantic Learning (Meta-SeL). Meta-SeL is an integrated framework that leverages two input 3D local points (input 3D models and part-segmentation labels), providing a time and cost-efficient, and precise projection model for a number of 3D recognition tasks. The results indicate that Meta-SeL yields competitive performance in comparison with other complex state-of-the-art work. Moreover, being random shuffle invariant, Meta-SeL is resilient to translation as well as jittering noise.