# SLTNet: Efficient Event-based Semantic Segmentation with Spike-driven Lightweight Transformer-based Networks

arXiv: https://arxiv.org/abs/2412.12843 · HTML: https://mlsanity.com/paper/2412.12843/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [A Review on Deep Learning Techniques Applied to Semantic Segmentation](https://mlsanity.com/paper/1704.06857/) (2017)
- [Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips](https://mlsanity.com/paper/2404.03663/) (2024)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)
- [DDD17: End-To-End DAVIS Driving Dataset](https://mlsanity.com/paper/1711.01458/) (2017)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation](https://mlsanity.com/paper/2110.07742/) (2021)
- [EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation](https://mlsanity.com/paper/2111.12341/) (2021)
- [Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation](https://mlsanity.com/paper/2109.01801/) (2021)
- [EventDrop: data augmentation for event-based learning](https://mlsanity.com/paper/2106.05836/) (2021)
- [Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation](https://mlsanity.com/paper/2405.06228/) (2024)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios](https://mlsanity.com/paper/2409.11205/) (2024)
- [EvSegSNN: Neuromorphic Semantic Segmentation for Event Data](https://mlsanity.com/paper/2406.14178/) (2024)
- [SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation](https://mlsanity.com/paper/2405.06525/) (2024)
- [Semantics from Space: Satellite-Guided Thermal Semantic Segmentation Annotation for Aerial Field Robots](https://mlsanity.com/paper/2403.14056/) (2024)
- [A Novel Wide-Area Multiobject Detection System with High-Probability Region Searching](https://mlsanity.com/paper/2405.04589/) (2024)

## Built on by (most cited first, 1 of 1)

- [MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation](https://mlsanity.com/paper/2512.24243/) (2025)

## Abstract (arXiv)

Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at most 9.06% and 9.39% mIoU, respectively, with extremely 4.58x lower energy consumption and 114 FPS inference speed. Our code is open-sourced and available at https://github.com/longxianlei/SLTNet-v1.0.