mlsanityData to 7 Oct 2026

Object Detection as Probabilistic Set Prediction

arXiv 2203.07980 ↗First posted 15 Mar 2022cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems. The development and evaluation of probabilistic object detectors have been hindered by shortcomings in existing performance measures, which tend to involve arbitrary thresholds or limit the detector's choice of distributions. In this work, we propose to view object detection as a set prediction task where detectors predict the distribution over the set of objects. Using the negative log-likelihood for random finite sets, we present a proper scoring rule for evaluating and training probabilistic object detectors. The proposed method can be applied to existing probabilistic detectors, is free from thresholds, and enables fair comparison between architectures. Three different types of detectors are evaluated on the COCO dataset. Our results indicate that the training of existing detectors is optimized toward non-probabilistic metrics. We hope to encourage the development of new object detectors that can accurately estimate their own uncertainty. Code available at https://github.com/georghess/pmb-nll.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

24 of 37 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2020Rethinking Transformer-based Set Prediction for Object Detectioncited by 156
  9. 2021Probabilistic two-stage detectioncited by 130
  10. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  11. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  12. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
12 more
  1. 2019Deep Set Prediction Networkscited by 71
  2. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  3. 2019Reliable training and estimation of variance networkscited by 63
  4. 2018Probabilistic Object Detection: Definition and Evaluationcited by 55
  5. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  6. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  7. 2017Poisson multi-Bernoulli mixture filter: direct derivation and implementationcited by 29
  8. 2020Localization Uncertainty Estimation for Anchor-Free Object Detectioncited by 19
  9. 2021I Find Your Lack of Uncertainty in Computer Vision Disturbingcited by 16
  10. 2019Capturing Object Detection Uncertainty in Multi-Layer Grid Mapscited by 10
  11. 2021An Uncertainty-Aware Performance Measure for Multi-Object Trackingcited by 9
  12. 2019Scaling Data Association for Hypothesis-Oriented MHTcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2024On permutation-invariant neural networkscited by 10
  2. 2023Label Dependencies-aware Set Prediction Networks for Multi-label Text Classificationcited by 1
  3. 2023Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Taskscited by 1