SA-MLP: A Low-Power Multiplication-Free Deep Network for 3D Point Cloud Classification in Resource-Constrained Environments

TL;DR

This paper introduces SA-MLP, a low-power, multiplication-free deep neural network architecture for 3D point cloud classification, optimized for resource-constrained environments, combining shift and adder layers for efficiency and accuracy.

Contribution

The paper proposes SA-MLP, a hybrid shift-adder architecture that enhances efficiency and performance over traditional multiplication-based models for point cloud classification.

Findings

SA-MLP outperforms baseline models in accuracy.

Add-MLP and Shift-MLP achieve competitive results with Mul-MLP.

SA-MLP delivers high accuracy with reduced computational cost.

Abstract

Point cloud classification plays a crucial role in the processing and analysis of data from 3D sensors such as LiDAR, which are commonly used in applications like autonomous vehicles, robotics, and environmental monitoring. However, traditional neural networks, which rely heavily on multiplication operations, often face challenges in terms of high computational costs and energy consumption. This study presents a novel family of efficient MLP-based architectures designed to improve the computational efficiency of point cloud classification tasks in sensor systems. The baseline model, Mul-MLP, utilizes conventional multiplication operations, while Add-MLP and Shift-MLP replace multiplications with addition and shift operations, respectively. These replacements leverage more sensor-friendly operations that can significantly reduce computational overhead, making them particularly suitable for resource-constrained sensor platforms. To further enhance performance, we propose SA-MLP, a hybrid architecture that alternates between shift and adder layers, preserving the network depth while optimizing computational efficiency. Unlike previous approaches such as ShiftAddNet, which increase the layer count and limit representational capacity by freezing shift weights, SA-MLP fully exploits the complementary advantages of shift and adder layers by employing distinct learning rates and optimizers. Experimental results show that Add-MLP and Shift-MLP achieve competitive performance compared to Mul-MLP, while SA-MLP surpasses the baseline, delivering results comparable to state-of-the-art MLP models in terms of both classification accuracy and computational efficiency. This work offers a promising, energy-efficient solution for sensor-driven applications requiring real-time point cloud classification, particularly in environments with limited computational resources.