# Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving

arXiv: https://arxiv.org/abs/2411.18860 · HTML: https://mlsanity.com/paper/2411.18860/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 25 of 25)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Adaptive Risk Minimization: Learning to Adapt to Domain Shift](https://mlsanity.com/paper/2007.02931/) (2020)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [Revisiting Batch Normalization for Improving Corruption Robustness](https://mlsanity.com/paper/2010.03630/) (2020)
- [AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation](https://mlsanity.com/paper/2304.12566/) (2023)
- [Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving](https://mlsanity.com/paper/2303.17297/) (2023)
- [The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection](https://mlsanity.com/paper/2112.14023/) (2021)
- [On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion](https://mlsanity.com/paper/2308.09942/) (2023)
- [Test time Adaptation through Perturbation Robustness](https://mlsanity.com/paper/2110.10232/) (2021)
- [Fully Test-Time Adaptation for Monocular 3D Object Detection](https://mlsanity.com/paper/2405.19682/) (2024)

## Built on by (most cited first, 1 of 1)

- [A DVDrive Approach for doScenes Instructed Driving Challenge](https://mlsanity.com/paper/2606.21623/) (2026)

## Abstract (arXiv)

In current open real-world autonomous driving scenarios, challenges such as sensor failure and extreme weather conditions hinder the generalization of most autonomous driving perception models to these unseen domain due to the domain shifts between the test and training data. As the parameter scale of autonomous driving perception models grows, traditional test-time adaptation (TTA) methods become unstable and often degrade model performance in most scenarios. To address these challenges, this paper proposes two new robust methods to improve the Batch Normalization with TTA for object detection in autonomous driving: (1) We introduce a LearnableBN layer based on Generalized-search Entropy Minimization (GSEM) method. Specifically, we modify the traditional BN layer by incorporating auxiliary learnable parameters, which enables the BN layer to dynamically update the statistics according to the different input data. (2) We propose a new semantic-consistency based dual-stage-adaptation strategy, which encourages the model to iteratively search for the optimal solution and eliminates unstable samples during the adaptation process. Extensive experiments on the NuScenes-C dataset shows that our method achieves a maximum improvement of about 8% using BEVFormer as the baseline model across six corruption types and three levels of severity. We will make our source code available soon.