Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning recurrent dynamics in spiking networks
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
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 MakingSequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods
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 TheoryDS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention
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…
DenoisingLearning spatiotemporal signals using a recurrent spiking network that discretizes time
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…