EventSSEG: Event-driven Self-Supervised Segmentation with Probabilistic Attention
This work addresses the challenge of low-latency, low-compute road segmentation for autonomous vehicles by leveraging event cameras, though it is incremental as it builds on existing event camera and self-supervised learning techniques.
The paper tackles road segmentation for autonomous vehicles using event cameras by introducing EventSSEG, a method that employs event-based self-supervised learning and probabilistic attention to eliminate the need for extensive labeled data. It achieves state-of-the-art performance on DSEC-Semantic and DDD17 datasets with minimal labeled events.
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.