Parameter-Efficient Fine-Tuning for Spiking Point Cloud Models

2026/07/31 by Zihao Guo, Jihua Zhu, Yiding Sun +2
Computer Science · #cs.CV

paper · pdf

arxiv created 2026/07/31 · arxiv updated 2026/08/03

Abstract

Spiking Neural Networks (SNNs) offer energy-efficient solutions for point cloud analysis on resource-constrained devices through event-driven computation. However, existing pre-trained spiking point cloud models rely on full fine-tuning for downstream task adaptation, incurring substantial parameter and storage overhead. Furthermore, binary spike propagation suppresses task-relevant sub-threshold information. To address these issues, we propose SpikePEFT, the first parameter-efficient fine-tuning framework for spiking point cloud models. Specifically, Intrinsic Dynamics Tuning (IDT) adaptively modulates membrane decay and firing thresholds, enabling efficient neuron-intrinsic adaptation while keeping the pre-trained synaptic transformations frozen. Moreover, Silent-State Disambiguation Adaptation (SSDA) recovers task-relevant information from informative silent states, thereby providing richer evidence for downstream adaptation. Extensive experiments across multiple benchmarks demonstrate the effectiveness and efficiency of SpikePEFT. In particular, our method achieves 92.4% accuracy on ModelNet40 and 85.6% on the most challenging classification split ScanObjectNN(PB_T50_RS) while updating only about 5% of the trainable parameters and preserving the energy efficiency of SNNs. This work provides a promising step toward parameter-efficient adaptation of neuromorphic vision models.

Citations

• Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
• PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models
• SVL: Spike-based Vision-language Pretraining for Efficient 3D Open-world Understanding
• PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
• MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
• Efficient 3D Recognition with Event-driven Spike Sparse Convolution
• Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Spiking PointNet: Spiking Neural Networks for Point Clouds
• SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
• Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy
• Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
• Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Revisiting Point Cloud Classification: A New Benchmark Dataset and\n Classification Model on Real-World Data
• Relation-Shape Convolutional Neural Network for Point Cloud Analysis
• Parameter-Efficient Transfer Learning for NLP
• Dynamic Graph CNN for Learning on Point Clouds
• Dynamic Graph CNN for Learning on Point Clouds
• Attention Is All You Need
• A scalable active framework for region annotation in 3D shape collections