提出双阈值方法，在保证置信度前提下自适应拒答高风险预测。
Beyond Confidence: Adaptive Abstention in Dual-Threshold Conformal Prediction for Autonomous System Perception
- 用双重阈值实现统计保真覆盖与高风险场景拒答
- 环境恶化时拒答率13.5%~63.4%，检测AUC达0.993~0.995
- 适用于自动驾驶等安全关键系统，尤其对激光雷达感知表现优异
安全关键的感知系统需要可靠的不确定性量化和合理的拒答机制以保障复杂工况下的安全性。本文提出一种新型双阈值置信区间框架，提供统计保证的不确定性估计，并在高风险场景中实现选择性预测。该方法结合置信阈值（确保预测集覆盖概率≥1−α）与通过ROC分析优化的拒答阈值，实现无分布覆盖保证的同时识别不可靠预测。在CIFAR-100、ImageNet1K和ModelNet40数据集上，针对相机与激光雷达模态的多种环境扰动进行评估，结果表明：在严重条件下检测性能优异（AUC: 0.993–0.995），覆盖率达>90.0%，拒答比例随环境恶化从13.5%增至63.4%（±0.5）。激光雷达感知中，框架保持稳健覆盖（>84.5%）并合理拒答不可靠预测。在强扰动下，检测性能（AUC: 0.995±0.001）显著优于现有方法。本方法统一理论保证与实际部署需求，为复杂现实条件下的安全关键自主系统提供鲁棒解决方案。
原文摘要 · Abstract (English)
Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework that provides statistically-guaranteed uncertainty estimates while enabling selective prediction in high-risk scenarios. Our approach uniquely combines a conformal threshold ensuring valid prediction sets with an abstention threshold optimized through ROC analysis, providing distribution-free coverage guarantees (>= 1 - alpha) while identifying unreliable predictions. Through comprehensive evaluation on CIFAR-100, ImageNet1K, and ModelNet40 datasets, we demonstrate superior robustness across camera and LiDAR modalities under varying environmental perturbations. The framework achieves exceptional detection performance (AUC: 0.993 to 0.995) under severe conditions while maintaining high coverage (>90.0%) and enabling adaptive abstention (13.5% to 63.4% +/- 0.5) as environmental severity increases. For LiDAR-based perception, our approach demonstrates particularly strong performance, maintaining robust coverage (>84.5%) while appropriately abstaining from unreliable predictions. Notably, the framework shows remarkable stability under heavy perturbations, with detection performance (AUC: 0.995 +/- 0.001) significantly outperforming existing methods across all modalities. Our unified approach bridges the gap between theoretical guarantees and practical deployment needs, offering a robust solution for safety-critical autonomous systems operating in challenging real-world conditions.
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。