# Probabilistic Object Detection with Conformal Prediction Source: [Probabilistic Object Detection with Conformal Prediction]() Collection index: [llms.txt]() Data updated: 2026-05-12T05:00:12.036Z Authors: Christopher Ries, Moussa Kassem Sbeyti, Nicolas Bianco, Nadja Klein Published: 2026-05-08T10:23:43.000Z ## Abstract Conformal Prediction (CP) is a distribution-free method for constructing prediction sets with marginal finite-sample coverage guarantees, making it a suitable framework for reliable uncertainty quantification in safety-critical object detection. However, object detection introduces structured multi-output predictions, complicating the application of classical CP theory developed for single outputs. In addition, standard, unscaled CP produces fixed-width prediction intervals across inputs, leading to unnecessary width for low-uncertainty predictions. While scaled CP addresses this by adapting the interval width to an input-dependent uncertainty estimate, prior work has neither systematically compared unscaled and scaled CP for multi-class object detection, nor integrated CP with a complementary uncertainty quantification method in this setting. We fill this gap by: (i) applying CP coordinate-wise to bounding box corners with a Bonferroni correction for box-level guarantees; (ii) scaling the resulting intervals using per-prediction aleatoric uncertainty estimates derived from a probabilistic object detector trained with loss attenuation, evaluated in uncalibrated and two calibrated variants; (iii) extending to a two-step pipeline that constructs prediction sets for the class using RAPS and conditions the conformalized bounding boxes on the predicted class set. Across three autonomous driving datasets (KITTI, BDD, CODA), including a cross-domain setting under distribution shift, scaled CP consistently improves interval sharpness over unscaled CP, achieving up to 19% higher IoU and 39% lower interval scores, without sacrificing coverage. Class-wise calibration further improves coverage for both variants with a negligible effect on sharpness. Together, these improvements yield more actionable uncertainty estimates for real-time, real-world object detection. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Bounding Box Regression on KITTI 1589 predictions (80/20 split)](): Bounding Box Regression; KITTI 1589 predictions (80/20 split); Coverage: 72. - [Bounding Box Regression on BDD 37189 predictions (80/20 split)](): Bounding Box Regression; BDD 37189 predictions (80/20 split); Coverage: 72. - [Bounding Box Regression on CODA 4931 predictions (80/20 split)](): Bounding Box Regression; CODA 4931 predictions (80/20 split); Coverage: 70. - [Multi-class Object Detection on KITTI 1589 (80/20 evaluation)](): Multi-class Object Detection; KITTI 1589 (80/20 evaluation); Covariance: 88. ## Original sources and implementation [Original paper]() [PDF]()