# Ultra-Low-Latency Spiking Neural Networks with Temporal-Dependent Integrate-and-Fire Neuron Model for Objects Detection

## TL;DR

This paper introduces a novel temporal-dependent neuron model for spiking neural networks that enhances object detection performance with ultra-low latency, maintaining energy efficiency and surpassing existing conversion methods.

## Contribution

The paper proposes a new tdIF neuron architecture and delay-spike approach, enabling SNNs to achieve high accuracy in visual detection tasks with minimal time-steps.

## Key findings

- Achieves state-of-the-art detection performance with 5 or fewer time-steps.
- Maintains energy efficiency comparable to traditional IF neurons.
- Outperforms existing ANN-SNN conversion methods in detection tasks.

## Abstract

Spiking Neural Networks (SNNs), inspired by the brain, are characterized by minimal power consumption and swift inference capabilities on neuromorphic hardware, and have been widely applied to various visual perception tasks. Current ANN-SNN conversion methods have achieved excellent results in classification tasks with ultra-low time-steps, but their performance in visual detection tasks remains suboptimal. In this paper, we propose a delay-spike approach to mitigate the issue of residual membrane potential caused by heterogeneous spiking patterns. Furthermore, we propose a novel temporal-dependent Integrate-and-Fire (tdIF) neuron architecture for SNNs. This enables Integrate-and-fire (IF) neurons to dynamically adjust their accumulation and firing behaviors based on the temporal order of time-steps. Our method enables spikes to exhibit distinct temporal properties, rather than relying solely on frequency-based representations. Moreover, the tdIF neuron maintains energy consumption on par with traditional IF neuron. We demonstrate that our method achieves more precise feature representation with lower time-steps, enabling high performance and ultra-low latency in visual detection tasks. In this study, we conduct extensive evaluation of the tdIF method across two critical vision tasks: object detection and lane line detection. The results demonstrate that the proposed method surpasses current ANN-SNN conversion approaches, achieving state-of-the-art performance with ultra-low latency (within 5 time-steps).