paper-with-me

홈 › Papers

Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation

2025-12-05 · Yiting Dong, Zhaofei Yu, Jianhao Ding, Zijie Xu, Tiejun Huang arxiv

Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism. However, existing research lack analysis of its actual contributions in complex temporal tasks. We design Non-Stateful (NS) models progressively removing membrane propagation to quantify its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow or deep layers improves performance, while excessive removal causes collapse. We attribute this to spatio-temporal resource competition where neurons encode both semantics and dynamics within limited range, with temporal state consuming capacity for spatial learning. Based on this, we propose Spatial-Temporal Separable Network (STSep), decoupling residual blocks into independent spatial and temporal branches. The spatial branch focuses on semantic extraction while the temporal branch captures motion through explicit temporal differences. Experiments on Something-Something V2, UCF101, and HMDB51 show STSep achieves superior performance, with retrieval task and attention analysis confirming focus on motion rather than static appearance. This work provides new perspectives on SNNs' temporal mechanisms and an effective solution for spatiotemporal modeling in video understanding.

📄 PDF Abstract BibTeX arXiv:2512.05472

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning recurrent dynamics in spiking networks

2018-03-18 · Christopher Kim, Carson Chow

Spiking activity of neurons engaged in learning and performing a task show complex spatiotemporal dynamics. While the output of recurrent network models can learn to perform various tasks, the possible range of recurrent…

Unleashing the Potential of Spiking Neural Networks for Sequential Modeling with Contextual Embedding

2023-08-29 · Xinyi Chen, Jibin Wu, Huajin Tang, Qinyuan Ren 외

The human brain exhibits remarkable abilities in integrating temporally distant sensory inputs for decision-making. However, existing brain-inspired spiking neural networks (SNNs) have struggled to match their biological…

Decision Making

Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods

2021-09-29 · ICLR 2022 4 · Xueyuan She, Saurabh Dash, Saibal Mukhopadhyay

A dynamical system of spiking neurons with only feedforward connections can classify spatiotemporal patterns without recurrent connections. However, the theoretical construct of a feedforward Spiking Neural Network (SNN)…

Gesture RecognitionImage ClassificationLearning Theory

DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention

2024-09-20 · Boxun Xu, Hejia Geng, Yuxuan Yin, Peng Li

Vision Transformers (ViT) are current high-performance models of choice for various vision applications. Recent developments have given rise to biologically inspired spiking transformers that thrive in ultra-low power op…

Denoising

Learning spatiotemporal signals using a recurrent spiking network that discretizes time

2019-07-20 · Amadeus Maes, Mauricio Barahona, Claudia Clopath

Learning to produce spatiotemporal sequences is a common task that the brain has to solve. The same neural substrate may be used by the brain to produce different sequential behaviours. The way the brain learns and encod…