Deeper or Wider Networks of Point Clouds with Self-attention?
arXiv:2011.14285
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.
The experiments is incompleted
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Self-Attention Generative Adversarial Networks
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
- Pay Less Attention with Lightweight and Dynamic Convolutions
- Stand-Alone Self-Attention in Vision Models
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
- PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
- Disentangled Non-Local Neural Networks