EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention

2025/08/20 by Lakshmi Annamalai, Annamalai, Lakshmi, Chetan Singh Thakur +1
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning and Data Classification #Neural Networks and Applications #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2508.14856

openalex publication_date 2025/08/20 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28

Abstract

Road segmentation is pivotal for autonomous vehicles, yet achieving low latency and low compute solutions using frame based cameras remains a challenge. Event cameras offer a promising alternative. To leverage their low power sensing, we introduce EventSSEG, a method for road segmentation that uses event only computing and a probabilistic attention mechanism. Event only computing poses a challenge in transferring pretrained weights from the conventional camera domain, requiring abundant labeled data, which is scarce. To overcome this, EventSSEG employs event-based self supervised learning, eliminating the need for extensive labeled data. Experiments on DSEC-Semantic and DDD17 show that EventSSEG achieves state of the art performance with minimal labeled events. This approach maximizes event cameras capabilities and addresses the lack of labeled events.

Citations

• OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies
• Exploiting Low-level Representations for Ultra-Fast Road Segmentation
• Hierarchical Neural Memory Network for Low Latency Event Processing
• Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
• Masked-attention Mask Transformer for Universal Image Segmentation
• Masked Autoencoders Are Scalable Vision Learners
• ResNet strikes back: An improved training procedure in timm
• BEiT: BERT Pre-Training of Image Transformers
• EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation
• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
• Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy
• ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data
• Hierarchical Multi-Scale Attention for Semantic Segmentation
• Video to Events: Recycling Video Datasets for Event Cameras
• High Speed and High Dynamic Range Video with an Event Camera
• Searching for MobileNetV3
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Attention Is All You Need
• Pyramid Scene Parsing Network
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Fully Convolutional Networks for Semantic Segmentation

Related

• A Large Scale Event-based Detection Dataset for Automotive
• Deep Event-based Object Detection in Autonomous Driving: A Survey
• R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild
• OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras
• Event-Free Moving Object Segmentation from Moving Ego Vehicle