mlsanityData to 7 Oct 2026

Localisation-Aware Uncertainty for Pretrained Object Detection

arXiv 2610.01409 ↗First posted 1 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Reliable uncertainty estimation is essential for deploying object detectors when distribution/covariate shift and adversarial attacks may occur. Existing approaches often require detector retraining, architectural modification, or repeated inference, which may be infeasible or incur significant overheads. We introduce a lightweight post-hoc evidential meta-model that learns when object localisations should be considered uncertain while keeping the base detector frozen. Our approach automatically identifies localisation-relevant features and uses saliency-guided modification to construct an increasingly challenging curriculum. Detection-level targets combine localisation error, modification level, and prediction instability to guide an evidential meta-model to estimate uncertainty for each predicted bounding box. Our approach requires no changes to the detector and preserves its original localisation outputs. Across adversarial attacks and evaluated strengths, GRACE improves TP-FP AUROC by 22% relative to the strongest comparator in some cases while maintaining in-distribution detection performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

26 of 34 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2016Variational Inference: A Review for Statisticianscited by 1,466
  8. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  9. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  10. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  11. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
  12. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
14 more
  1. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  2. 2019Deep Evidential Regressioncited by 354
  3. 2020Detection and Tracking Meet Drones Challengecited by 261
  4. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
  5. 2018High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approachcited by 117
  6. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  7. 2020Multivariate Confidence Calibration for Object Detectioncited by 98
  8. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  9. 2022Post-hoc Uncertainty Learning using a Dirichlet Meta-Modelcited by 31
  10. 2021Toward Explainable AI for Regression Modelscited by 30
  11. 2020MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detectioncited by 18
  12. 2023Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Modelscited by 15
  13. 2023Robust Uncertainty Quantification Using Conformalised Monte Carlo Predictioncited by 10
  14. 2020TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systemscited by 7

Built on by

Not cited yet.