用事件相机实现低延迟道路分割，无需大量标注数据
EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
- 仅用事件数据+概率注意力机制，实现自监督学习
- 在DSEC-Semantic和DDD17上达到当前最佳性能，标签数据极少
- 适合自动驾驶中低功耗实时感知场景
道路分割对自动驾驶至关重要，但基于帧的摄像头实现低延迟、低算力方案仍具挑战。事件相机提供了有前景的替代方案。为利用其低功耗感知优势，本文提出EventSSEG，一种仅依赖事件数据进行道路分割的方法，采用概率注意力机制。事件仅计算带来预训练权重迁移困难，需大量标注数据，而此类数据稀缺。为此，EventSSEG引入事件自监督学习，无需大量标注。在DSEC-Semantic和DDD17数据集上的实验表明，该方法以极少量标注事件实现了当前最优性能，充分释放了事件相机潜力，并缓解了标注数据不足问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。