RIPE-MambaSpike：用于参数高效事件视觉的分辨率无关尖峰状态空间接口
RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision
浏览论文内容
中文总结 AI 辅助
提出分辨率无关参数高效的RIPE-MambaSpike，以固定通道宽度的分层多分辨率桥接替代高成本投影，在紧凑参数下保持精度，并在多个事件视觉基准上达到最优。
中文摘要 AI 辅助
Spiking-Mamba混合模型在事件视觉上达到了较高的精度，但现有设计通常需要数千万个参数。大部分成本来自尖峰前端与状态空间骨干网络的连接方式，而非混合架构本身。在一个代表性模型中，单个依赖分辨率的投影就占据了36.25M参数中的33.55M。为此，我们提出了RIPE-MambaSpike（分辨率无关、参数高效），用固定通道宽度的分层多分辨率桥接取代该投影。其部署参数量为0.870M，在输入面积43倍范围内，固定时间步和宽度下保持不变。重参数化尖峰阶段、时间解耦调制以及动态凸包界双流膜电位注意力，在紧凑设计下保持了精度。在结果上，RIPE-MambaSpike在CIFAR10-DVS、N-Caltech101和DailyDVS-200上达到帕累托最优。值得注意的是，在200类DailyDVS-200上，缩放后的8.04M配置实现了45.7%的top-1精度，是该基准上报告的最佳尖峰结果，并且比密集ANN的参数少3.0-15.1倍。总体而言，我们的发现表明，竞争性的事件识别并不需要依赖分辨率的参数增长。代码可在该https URL获取。
英文摘要
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.
