增强恶劣天气条件下的自动驾驶分割能力：一种面向SAM优化的双不确定性感知训练方法
Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
- Queen's University（女王大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对SAM等视觉基础模型在恶劣天气下自动驾驶分割表现不佳的问题，提出两种不确定性感知优化方法，经多数据集验证有效提升了分割鲁棒性，为安全自动驾驶提供支撑。
AI中文摘要：
视觉基础模型（如Segment Anything Model（SAM，分割一切模型）及其继任者SAM2）的最新进展，在通用图像分割基准上取得了当前最优性能。但这些模型在视觉模糊度较高的恶劣天气条件下表现不佳，主要原因是缺乏不确定性量化。医学成像领域的不确定性感知训练已提升了模糊场景下的可靠性受此启发，我们研究了两种增强自动驾驶分割鲁棒性的方法。首先，我们提出了一种SAM2的多步微调流程，将不确定性指标直接纳入损失函数，提升了整体场景识别效果。其次，我们将原本为医学图像分割设计的Uncertainty-Aware Adapter（UAT，不确定性感知适配器）适配到驾驶场景中。我们在CamVid、BDD100K和GTA驾驶数据集上评估了这两种方法。实验表明，UAT-SAM在极端天气下表现优于标准SAM，而采用不确定性感知损失的SAM2在多样驾驶场景中均实现了性能提升。这些发现凸显了显式不确定性建模对于挑战性环境下安全关键型自动驾驶的重要价值。
英文摘要：
Recent advances in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have achieved state-of-the-art performance on general image segmentation benchmarks. However, these models struggle in adverse weather conditions where visual ambiguity is high, largely due to their lack of uncertainty quantification. Inspired by progress in medical imaging, where uncertainty-aware training has improved reliability in ambiguous cases, we investigate two approaches to enhance segmentation robustness for autonomous driving. First, we introduce a multi-step finetuning procedure for SAM2 that incorporates uncertainty metrics directly into the loss function, improving overall scene recognition. Second, we adapt the Uncertainty-Aware Adapter (UAT), originally designed for medical image segmentation, to driving contexts. We evaluate both methods on CamVid, BDD100K, and GTA driving datasets. Experiments show that UAT-SAM outperforms standard SAM in extreme weather, while SAM2 with uncertainty-aware loss achieves improved performance across diverse driving scenes. These findings underscore the value of explicit uncertainty modeling for safety-critical autonomous driving in challenging environments.
