POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
This work addresses efficiency in point cloud processing for computer vision tasks on resource-limited devices, representing an incremental improvement in binary neural network methods.
The paper tackles the computational challenge of real-time point cloud processing on edge devices by introducing POEM, a method that integrates Expectation-Maximization into binary neural networks to constrain weights and learn scale factors, achieving up to 6.7% improvement over state-of-the-art binary point cloud networks.
Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices. To address this issue, we implement XNOR-Net-based binary neural networks (BNNs) for an efficient point cloud processing, but its performance is severely suffered due to two main drawbacks, Gaussian-distributed weights and non-learnable scale factor. In this paper, we introduce point-wise operations based on Expectation-Maximization (POEM) into BNNs for efficient point cloud processing. The EM algorithm can efficiently constrain weights for a robust bi-modal distribution. We lead a well-designed reconstruction loss to calculate learnable scale factors to enhance the representation capacity of 1-bit fully-connected (Bi-FC) layers. Extensive experiments demonstrate that our POEM surpasses existing the state-of-the-art binary point cloud networks by a significant margin, up to 6.7 %.