PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis

TL;DR

PointABM is a hybrid model combining state space models and Transformer architecture to improve local and global feature extraction in 3D point cloud analysis, demonstrating superior performance through extensive experiments.

Contribution

The paper introduces PointABM, integrating bidirectional state space models with Transformer self-attention for enhanced 3D point cloud analysis.

Findings

Significantly improves 3D point cloud classification accuracy

Effectively captures both local and global features

Outperforms existing methods in experiments

Abstract

Mamba, based on state space model (SSM) with its linear complexity and great success in classification provide its superiority in 3D point cloud analysis. Prior to that, Transformer has emerged as one of the most prominent and successful architectures for point cloud analysis. We present PointABM, a hybrid model that integrates the Mamba and Transformer architectures for enhancing local feature to improve performance of 3D point cloud analysis. In order to enhance the extraction of global features, we introduce a bidirectional SSM (bi-SSM) framework, which comprises both a traditional token forward SSM and an innovative backward SSM. To enhance the bi-SSM's capability of capturing more comprehensive features without disrupting the sequence relationships required by the bidirectional Mamba, we introduce Transformer, utilizing its self-attention mechanism to process point clouds. Extensive experimental results demonstrate that integrating Mamba with Transformer significantly enhance the model's capability to analysis 3D point cloud.