mlsanityData to 7 Oct 2026

Beyond Confidence: Adaptive Abstention in Dual-Threshold Conformal Prediction for Autonomous System Perception

arXiv 2502.07255 ↗First posted 11 Feb 2025cs.RO cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

29 of 43 references.

References · 29

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  6. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  10. 2020Classification with Valid and Adaptive Coveragecited by 390
  11. 2022Adaptive Conformal Predictions for Time Seriescited by 155
  12. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
17 more
  1. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  2. 2018Baidu Apollo EM Motion Plannercited by 99
  3. 2021Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigationcited by 47
  4. 2020Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptationcited by 43
  5. 2017Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developmentscited by 30
  6. 2017Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modelingcited by 25
  7. 2023Lightweight, Uncertainty-Aware Conformalized Visual Odometrycited by 13
  8. 2019Testing and verification of neural-network-based safety-critical control software: A systematic literature reviewcited by 12
  9. 2023Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edgecited by 9
  10. 2023Conformalized Multimodal Uncertainty Regression and Reasoningcited by 6
  11. 2023STARNet: Sensor Trustworthiness and Anomaly Recognition via Approximated Likelihood Regret for Robust Edge Autonomycited by 5
  12. 2024Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensingcited by 5
  13. 2025INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomycited by 5
  14. 2023Quantification of Uncertainties in Deep Learning-based Environment Perceptioncited by 4
  15. 2024Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precisioncited by 2
  16. 2020Temporal Calibrated Regularization for Robust Noisy Label Learningcited by 1
  17. 2024Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approachcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Learnable Conformal Prediction with Context-Aware Nonconformity Functions for Robotic Planning and Perceptioncited by 7
  2. 2026VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluationcited by 7
  3. 2025Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptationcited by 6
  4. 2026Uncertainty-Guided Inference-Time Depth Adaptation for Transformer-Based Visual Trackingcited by 3
  5. 2026TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Samecited by 3
  6. 2026Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasetscited by 2