SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

TL;DR

SpikeVideoFormer introduces a spike-driven video Transformer with linear temporal complexity and Hamming attention, achieving state-of-the-art performance and efficiency in various video vision tasks.

Contribution

It proposes a novel spike-driven attention mechanism and a linear complexity Transformer for video tasks, advancing SNN applications in video analysis.

Findings

Achieves over 15% improvement on pose tracking and segmentation tasks.

Matches recent ANN methods' performance with significant efficiency gains.

Maintains linear temporal complexity $ ext{O}(T)$ in video processing.

Abstract

Spiking Neural Networks (SNNs) have shown competitive performance to Artificial Neural Networks (ANNs) in various vision tasks, while offering superior energy efficiency. However, existing SNN-based Transformers primarily focus on single-image tasks, emphasizing spatial features while not effectively leveraging SNNs' efficiency in video-based vision tasks. In this paper, we introduce SpikeVideoFormer, an efficient spike-driven video Transformer, featuring linear temporal complexity $\mathcal{O}(T)$. Specifically, we design a spike-driven Hamming attention (SDHA) which provides a theoretically guided adaptation from traditional real-valued attention to spike-driven attention. Building on SDHA, we further analyze various spike-driven space-time attention designs and identify an optimal scheme that delivers appealing performance for video tasks, while maintaining only linear temporal complexity. The generalization ability and efficiency of our model are demonstrated across diverse downstream video tasks, including classification, human pose tracking, and semantic segmentation. Empirical results show our method achieves state-of-the-art (SOTA) performance compared to existing SNN approaches, with over 15\% improvement on the latter two tasks. Additionally, it matches the performance of recent ANN-based methods while offering significant efficiency gains, achieving $\times 16$, $\times 10$ and $\times 5$ improvements on the three tasks. https://github.com/JimmyZou/SpikeVideoFormer