mlsanityData to 7 Oct 2026

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

arXiv 1904.04620 ↗First posted 9 Apr 2019cs.CVcited by 105

Not on the map. Why?

Abstract (arXiv)

The use of object detection algorithms is becoming increasingly important in autonomous vehicles, and object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. A false positive (FP) from a false localization during autonomous driving can lead to fatal accidents and hinder safe and efficient driving. Therefore, a detection algorithm that can cope with mislocalizations is required in autonomous driving applications. This paper proposes a method for improving the detection accuracy while supporting a real-time operation by modeling the bounding box (bbox) of YOLOv3, which is the most representative of one-stage detectors, with a Gaussian parameter and redesigning the loss function. In addition, this paper proposes a method for predicting the localization uncertainty that indicates the reliability of bbox. By using the predicted localization uncertainty during the detection process, the proposed schemes can significantly reduce the FP and increase the true positive (TP), thereby improving the accuracy. Compared to a conventional YOLOv3, the proposed algorithm, Gaussian YOLOv3, improves the mean average precision (mAP) by 3.09 and 3.5 on the KITTI and Berkeley deep drive (BDD) datasets, respectively. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 42 frames per second (fps) and shows a higher accuracy than previous approaches with a similar fps. Therefore, the proposed algorithm is the most suitable for autonomous driving applications.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 23; 2023: 20; 2024: 19; 2025: 10; 2026: 8.

105 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  3. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  4. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  5. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  6. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  7. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  8. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  9. 2022Learning Domain Adaptive Object Detection with Probabilistic Teachercited by 57
  10. 2021Localization Distillation for Dense Object Detectioncited by 55
  11. 2022Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detectioncited by 45
  12. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
38 more
  1. 2024A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMscited by 35
  2. 2022Probabilistic Representations for Video Contrastive Learningcited by 33
  3. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  4. 2022Uncertainty-Aware Multi-View Representation Learningcited by 29
  5. 2022ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixingcited by 28
  6. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  7. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  8. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  9. 2021T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptationcited by 24
  10. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  11. 2022GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimationcited by 24
  12. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
  13. 2022Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehiclescited by 22
  14. 2021Monte Carlo DropBlock for Modelling Uncertainty in Object Detectioncited by 20
  15. 2021Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learningcited by 20
  16. 2022Localization Distillation for Object Detectioncited by 19
  17. 2023Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embeddingcited by 19
  18. 2021Auto-Encoding Score Distribution Regression for Action Quality Assessmentcited by 18
  19. 2023RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understandingcited by 17
  20. 2021I Find Your Lack of Uncertainty in Computer Vision Disturbingcited by 16
  21. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  22. 2023Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detectioncited by 16
  23. 2021CertainNet: Sampling-free Uncertainty Estimation for Object Detectioncited by 15
  24. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  25. 2024Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimationcited by 11
  26. 2025UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Networkcited by 11
  27. 2021Attention-based Neural Network for Driving Environment Complexity Perceptioncited by 9
  28. 2022GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 9
  29. 2024Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detectioncited by 9
  30. 2024SURE: SUrvey REcipes for building reliable and robust deep networkscited by 8
  31. 2025Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EMcited by 8
  32. 2021A Unified Light Framework for Real-time Fault Detection of Freight Train Imagescited by 7
  33. 2022Detecting Volunteer Cotton Plants in a Corn Field with Deep Learning on UAV Remote-Sensing Imagerycited by 7
  34. 2023Zone Evaluation: Revealing Spatial Bias in Object Detectioncited by 7
  35. 2023Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximizationcited by 7
  36. 2024Uncertainty-boosted Robust Video Activity Anticipationcited by 7
  37. 2021RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detectioncited by 6
  38. 2022Autoregressive Uncertainty Modeling for 3D Bounding Box Predictioncited by 6

50 most cited of 105 All 105 (JSON)