Research map / Detection and segmentation / CNN features
Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
Jiwoong Choi, Dayoung Chun, Hyun Kim, Hyuk-Jae Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Gaussian bbox modeling, NLL loss and uncertainty-aware detection criterion | YOLOv3 (512x512) · KITTI val | mAP: 80.52 -> 83.61 | Improved |
| add Gaussian bbox modeling, NLL loss and uncertainty-aware detection criterion | YOLOv3 (512x512) · BDD test | mAP: 14.9 -> 18.4 | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · COCO | AP: 36.1, 3.1 higher than YOLOv3 | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · COCO | AP75: 39.0, 4.6 higher than YOLOv3 | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · KITTI val | false positives: 1,681 -> 985 (-41.40%) | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · KITTI val | true positives: 13,575 -> 14,560 (+7.26%) | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · BDD val | false positives: 86,380 -> 51,296 (-40.62%) | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · BDD val | true positives: 57,261 -> 59,724 (+4.30%) | Improved |
| add Gaussian modeling and uncertainty criterion | YOLOv3 (512x512) · KITTI val | FPS: 43.57 -> 43.13 | No clear effect |
| add Gaussian modeling and uncertainty criterion | YOLOv3 · BDD test | FPS: 42.9 -> 42.5 | No clear effect |
| raise input resolution from 512x512 to 704x704 | Gaussian YOLOv3 · KITTI val | mAP: 83.61 -> 86.79 mAP, 43.13 -> 24.91 FPS | Mixed |
| raise input resolution from 512x512 to 736x736 | Gaussian YOLOv3 · BDD test | mAP: 18.4 -> 20.8 mAP, 42.5 -> 22.5 FPS | Mixed |
Closest papers by meaning
- 3D Object Detection for Autonomous Driving: A Comprehensive Survey (IJCV 2023 · similarity 0.85)
- YOLOv10: Real-Time End-to-End Object Detection (NeurIPS 2024 · similarity 0.85)
- 3D Object Detection From Images for Autonomous Driving: A Survey (TPAMI 2023 · similarity 0.84)
- GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving (CVPR 2019 · similarity 0.84)
- Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration (CVPR 2023 · similarity 0.84)
- GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
