Abstract
Semantic segmentation of outdoor street scenes plays a key role in applications such as autonomous driving, mobile robotics, and assistive technology for visually-impaired pedestrians. For these applications, accurately distinguishing between key surfaces and objects such as roads, sidewalks, vehicles, and pedestrians is essential for maintaining safety and minimizing risks. Semantic segmentation must be robust to different environments, lighting and weather conditions, and sensor noise, while being performed in real-time. We propose a region-level, uncertainty-gated retrieval mechanism that improves segmentation accuracy and calibration under domain shift. Our best method achieves an 11.3% increase in mean intersection-over-union while reducing retrieval cost by 87.5%, retrieving for only 12.5% of regions compared to 100% for always-on baseline.
Abstract (translated)
户外街道场景的语义分割在自动驾驶、移动机器人和视觉障碍行人辅助技术等应用中起着关键作用。对于这些应用而言，准确地区分道路、人行道、车辆和行人等关键表面和物体是确保安全性和减少风险所必需的。为了适应不同的环境条件、光照和天气状况以及传感器噪声，并实现实时处理，语义分割必须具备鲁棒性。我们提出了一种基于区域级别的不确定性门控检索机制，该机制在领域偏移（domain shift）情况下提高了分割精度并改善了校准性能。我们的最佳方法实现了11.3%的平均交并比（mean intersection-over-union, mIoU）提升，并将检索成本降低了87.5%，仅对12.5%的区域进行检索，而基线系统则为100%全时段运行。
URL
https://arxiv.org/abs/2512.18082
