🤖 AI Summary
To address the demand for low-power, real-time 3D point cloud classification on resource-constrained edge devices (e.g., autonomous vehicles and robots), this paper proposes SA-MLP—a multiplication-free, lightweight MLP architecture. Methodologically, it introduces (1) an alternating Shift-Adder hybrid layer that replaces multiplications with bit-shifts and additions, enabling dynamic co-optimization of representational capacity and energy efficiency; and (2) a hierarchical learning rate scheduling scheme with layer-wise optimizers, overcoming conventional weight-freezing constraints to enhance training stability and accuracy. Evaluated on ModelNet40, SA-MLP achieves competitive accuracy relative to state-of-the-art MLP-based models while eliminating all multiplicative operations. It reduces inference energy consumption by over 60% and meets stringent embedded-system latency requirements for real-time deployment.
📝 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.