Activation-wise Propagation: A Universal Strategy to Break Timestep Constraints in Spiking Neural Networks for 3D Data Processing
Due to their event-driven and parameter-efficient effect, spiking neural networks (SNNs) show potential in tasks requiring real-time multi-sensor perception, such as autonomous driving. The spiking mechanism facilitates sparse encoding, enabling spatial and temporal data to be represented in a discrete manner. However, SNNs still lag behind artificial neural networks (ANNs) in terms of performance and computational efficiency. One major challenge in SNNs is the timestep-wise iterative update of neuronal states, which makes it difficult to achieve an optimal trade-off among accuracy, latency, and training cost. Although some methods perform well with shorter timesteps, few propose strategies to overcome such constraint effectively. Moreover, many recent SNN advancements rely on either optimizations tailored to specific architectures or a collection of specialized neuron-level strategies. While these approaches can enhance performance, they often lead to increased computational expense and restrict their application to particular architectures or modalities. This leaves room for further exploration of simple, universal, and structure-agnostic strategies that could offer broader applicability and efficiency. In this paper, we introduce Activation-wise Membrane Potential Propagation (AMP2), a novel state update mechanism for spiking neurons. Inspired by skip connections in deep networks, AMP2 incorporates the membrane potential of neurons into network, eliminating the need for iterative updates. Our method achieves significant improvements across various 3D modalities, including 3D point clouds and event streams, boosting Spiking PointNet's accuracy on ModelNet40 from 87.36% to 89.74% and surpassing ANN PointNet in recognition accuracy on the DVS128 Gesture dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionAutonomous DrivingComputational EfficiencyScene SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AI Security Leaderboard: Methodology, Results and Minimal Standard
Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developer…
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promis…
Computational EfficiencyClapping: Removing Per-sample Storage for Pipeline Parallel Distributed Optimization with Communication Compression
Pipeline-parallel distributed optimization is essential for large-scale machine learning but is challenged by significant communication overhead from transmitting high-dimensional activations and gradients between worker…
Distributed OptimizationASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack
Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful request…
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos, and show that it predicts a simple, no-cost change to standard practice: \emph{front-loaded} dropout schedu…