轻量级雷达相机深度估计模型，提升可解释性与鲁棒性
XD-RCDepth: Lightweight Radar-Camera Depth Estimation with Explainability-Aligned and Distribution-Aware Distillation
- 通过可解释性对齐与分布感知的蒸馏策略压缩模型
- 参数减少29.7%，MAE降低7.97%，实时运行于nuScenes和ZJU-4DRadarCam
- 适合自动驾驶中需高效高可信深度感知的场景
深度估计在自动驾驶中至关重要，雷达-相机融合能在恶劣条件下提供互补的几何线索，增强系统鲁棒性。本文提出XD-RCDepth，一种轻量级架构，在相比当前最优轻量级基线减少29.7%参数的同时保持相近精度。为在压缩下维持性能并提升可解释性，提出两种知识蒸馏策略：可解释性对齐蒸馏，将教师模型的显著性结构迁移至学生模型；深度分布蒸馏，将深度回归重构为离散区间上的软分类。二者结合使平均绝对误差（MAE）相较直接训练降低7.97%，并在nuScenes与ZJU-4DRadarCam数据集上实现竞争性精度与实时效率。代码已开源。
原文摘要 · Abstract (English)
Depth estimation remains central to autonomous driving, and radar-camera fusion offers robustness in adverse conditions by providing complementary geometric cues. In this paper, we present XD-RCDepth, a lightweight architecture that reduces the parameters by 29.7% relative to the state-of-the-art lightweight baseline while maintaining comparable accuracy. To preserve performance under compression and enhance interpretability, we introduce two knowledge-distillation strategies: an explainability-aligned distillation that transfers the teacher's saliency structure to the student, and a depth-distribution distillation that recasts depth regression as soft classification over discretized bins. Together, these components reduce the MAE compared with direct training with 7.97% and deliver competitive accuracy with real-time efficiency on nuScenes and ZJU-4DRadarCam datasets. Code: https://github.com/harborsarah/XD_RCDepth
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。