Spiking neural network design slashes parameters for event vision
RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision
Computer Vision and Pattern RecognitionNeural and Evolutionary Computing
Summary
Event-based vision systems let computers see and react like human eyes by processing changes rather than full images. But using spiking neural networks to do this usually needs huge numbers of parameters, making them hard to run efficiently. The authors made a new design called RIPE-MambaSpike that cuts this parameter count drastically without losing accuracy by changing how the system handles different image resolutions. Their method works well on several benchmark datasets and sets a new accuracy record on a challenging dataset using fewer resources than previous methods.
What this means in practice
- •For mobile app developers: Create lightweight event-based vision apps that use spiking networks with far fewer parameters to run efficiently on mobile devices.
- •For embedded systems engineers: Design compact vision modules for devices like drones or robots that process event data without large memory demands.
- •For security camera manufacturers: Develop event-driven cameras that achieve high accuracy for complex scenes using spiking models but with reduced hardware costs.$Commercial implications: Enables efficient event-based vision hardware with high accuracy and fewer parameters, lowering production costs for security cameras.
Authors
Md Muhiminul Islam, Shoaib Ahmed Dipu, Sayeed Shafayet Chowdhury
Abstract
Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost comes from how the spiking front-end is connected to the state-space backbone rather than from the hybrid architecture itself. In a representative model, a single resolution-dependent projection accounts for 33.55M of 36.25M parameters. To that end, we introduce RIPE-MambaSpike (Resolution-Independent, Parameter-Efficient), which replaces that projection with a hierarchical multi-resolution bridge of fixed channel width. Its deployed footprint is 0.870M parameters, constant at fixed time steps and widths across a 43x range of input areas. Reparameterized spiking stages, temporal decoupled modulation, and a dynamic convex-hull-bounded dual-stream membrane-potential attention preserve accuracy under this compact design. Result-wise, RIPE-MambaSpike is pareto-optimal on CIFAR10-DVS, N-Caltech101, and DailyDVS-200. Notably, on the 200-class DailyDVS-200, a scaled 8.04M configuration achieves 45.7% top-1 accuracy, the best reported spiking result on that benchmark, and outperforms prior spiking methods with 3.0-15.1x fewer parameters than dense ANNs. Overall, our findings demonstrate that competitive event-based recognition does not require resolution-dependent parameter growth. Code is available at https://github.com/MuhiminOsim/RIPE-MambaSpike.