# Reducing Overconfidence Predictions for Autonomous Driving Perception

arXiv: https://arxiv.org/abs/2202.07825 · HTML: https://mlsanity.com/paper/2202.07825/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 96 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 30 of 42)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks](https://mlsanity.com/paper/2002.10118/) (2020)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning](https://mlsanity.com/paper/2003.07329/) (2020)
- [Addressing Failure Prediction by Learning Model Confidence](https://mlsanity.com/paper/1910.04851/) (2019)
- [Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art](https://mlsanity.com/paper/1704.05519/) (2017)
- [Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models](https://mlsanity.com/paper/1808.01688/) (2018)
- [Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection](https://mlsanity.com/paper/1804.05132/) (2018)
- [The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes](https://mlsanity.com/paper/1903.01568/) (2019)
- [Distribution-free binary classification: prediction sets, confidence intervals and calibration](https://mlsanity.com/paper/2006.10564/) (2020)
- [A*3D Dataset: Towards Autonomous Driving in Challenging Environments](https://mlsanity.com/paper/1909.07541/) (2019)
- [ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving](https://mlsanity.com/paper/1811.12222/) (2018)
- [A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference](https://mlsanity.com/paper/1901.02731/) (2019)

## Built on by (most cited first, 7 of 7)

- [C2GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning](https://mlsanity.com/paper/2509.23129/) (2025)
- [Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications](https://mlsanity.com/paper/2402.08208/) (2024)
- [Quantum-Cognitive Neural Networks: Assessing Confidence and Uncertainty with Human Decision-Making Simulations](https://mlsanity.com/paper/2412.08010/) (2024)
- [WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling](https://mlsanity.com/paper/2506.23782/) (2025)
- [Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood](https://mlsanity.com/paper/2512.07390/) (2025)
- [Reducing the False Positive Rate Using Bayesian Inference in Autonomous Driving Perception](https://mlsanity.com/paper/2310.05951/) (2023)
- [Fine-Grained Uncertainty Quantification via Collisions](https://mlsanity.com/paper/2411.12127/) (2024)

## Abstract (arXiv)

In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs. Such layers often produce overconfident predictions rather than proper probabilistic scores, which can thus harm the decision-making of `critical' perception systems applied in autonomous driving and robotics. Given this, the experiments in this work propose a probabilistic approach based on distributions calculated out of the Logit layer scores of pre-trained networks. We demonstrate that Maximum Likelihood (ML) and Maximum a-Posteriori (MAP) functions are more suitable for probabilistic interpretations than SoftMax and Sigmoid-based predictions for object recognition. We explore distinct sensor modalities via RGB images and LiDARs (RV: range-view) data from the KITTI and Lyft Level-5 datasets, where our approach shows promising performance compared to the usual SoftMax and Sigmoid layers, with the benefit of enabling interpretable probabilistic predictions. Another advantage of the approach introduced in this paper is that the ML and MAP functions can be implemented in existing trained networks, that is, the approach benefits from the output of the Logit layer of pre-trained networks. Thus, there is no need to carry out a new training phase since the ML and MAP functions are used in the test/prediction phase.