Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention
This work addresses a bottleneck in 3D point cloud understanding for computer vision applications, offering an incremental improvement over existing attention mechanisms.
The paper tackled the problem of standard self-attention producing similar attention maps across queries in 3D point cloud processing, which hinders learning query-independent and query-dependent information, by proposing a unary-pairwise attention (UPA) that operates locally; it outperformed self-attention on tasks like shape classification and part segmentation, and enhanced PointNet++ to match or exceed state-of-the-art attention-based methods.
We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module.