# Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving

arXiv: https://arxiv.org/abs/2002.00216 · HTML: https://mlsanity.com/paper/2002.00216/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2020.

## Built on by (most cited first, 12 of 12)

- [HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection](https://mlsanity.com/paper/2206.15157/) (2022)
- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [DeepFusion: A Robust and Modular 3D Object Detector for Lidars, Cameras and Radars](https://mlsanity.com/paper/2209.12729/) (2022)
- [Generating Evidential BEV Maps in Continuous Driving Space](https://mlsanity.com/paper/2302.02928/) (2023)
- [Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift](https://mlsanity.com/paper/2106.00076/) (2021)
- [Uncertainty-Encoded Multi-Modal Fusion for Robust Object Detection in Autonomous Driving](https://mlsanity.com/paper/2307.16121/) (2023)
- [CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus](https://mlsanity.com/paper/2502.08169/) (2025)
- [Informative Data Selection with Uncertainty for Multi-modal Object Detection](https://mlsanity.com/paper/2304.11697/) (2023)
- [Data Fusion for Deep Learning on Transport Mode Detection: A Case Study](https://mlsanity.com/paper/2106.05876/) (2021)
- [Priors are Powerful: Improving a Transformer for Multi-camera 3D Detection with 2D Priors](https://mlsanity.com/paper/2301.13592/) (2023)
- [VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection](https://mlsanity.com/paper/2505.12715/) (2025)
- [GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving](https://mlsanity.com/paper/2606.16354/) (2026)

## Abstract (arXiv)

This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and leverage uncertainties to train the fusion network via a sampling mechanism. We validate our method on three datasets with challenging real-world driving scenarios. Experimental results show that the predicted uncertainties reflect complex environmental uncertainty like difficulties of a human expert to label objects. The results also show that our method consistently improves the Average Precision by up to 7% compared to the baseline method. When sensors are temporally misaligned, the sampling method improves the Average Precision by up to 20%, showing its high robustness against noisy sensor inputs.