Deeper or Wider Networks of Point Clouds with Self-attention?

TL;DR

This paper introduces SepNet, a point cloud network using groupwise self-attention to effectively capture local and global features, achieving state-of-the-art results in classification and segmentation tasks.

Contribution

The paper proposes groupwise self-attention as a novel building block for point cloud networks, enhancing local and global dependency modeling.

Findings

SepNet achieves state-of-the-art performance on multiple datasets.

Increasing width improves segmentation accuracy.

Increasing depth enhances classification performance.

Abstract

Prevalence of deeper networks driven by self-attention is in stark contrast to underexplored point-based methods. In this paper, we propose groupwise self-attention as the basic block to construct our network: SepNet. Our proposed module can effectively capture both local and global dependencies. This module computes the features of a group based on the summation of the weighted features of any point within the group. For convenience, we generalize groupwise operations to assemble this module. To further facilitate our networks, we deepen and widen SepNet on the tasks of segmentation and classification respectively, and verify its practicality. Specifically, SepNet achieves state-of-the-art for the tasks of classification and segmentation on most of the datasets. We show empirical evidence that SepNet can obtain extra accuracy in classification or segmentation from increased width or depth, respectively.