# In Rain or Shine: Understanding and Overcoming Dataset Bias for Improving Robustness Against Weather Corruptions for Autonomous Vehicles

arXiv: https://arxiv.org/abs/2204.01062 · HTML: https://mlsanity.com/paper/2204.01062/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [Identifying Unknown Instances for Autonomous Driving](https://mlsanity.com/paper/1910.11296/) (2019)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views](https://mlsanity.com/paper/2006.05518/) (2020)

## Built on by (most cited first, 3 of 3)

- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them](https://mlsanity.com/paper/2603.19852/) (2026)
- [t-RAIN: Robust generalization under weather-aliasing label shift attacks](https://mlsanity.com/paper/2305.08302/) (2023)

## Abstract (arXiv)

Several popular computer vision (CV) datasets, specifically employed for Object Detection (OD) in autonomous driving tasks exhibit biases due to a range of factors including weather and lighting conditions. These biases may impair a model's generalizability, rendering it ineffective for OD in novel and unseen datasets. Especially, in autonomous driving, it may prove extremely high risk and unsafe for the vehicle and its surroundings. This work focuses on understanding these datasets better by identifying such "good-weather" bias. Methods to mitigate such bias which allows the OD models to perform better and improve the robustness are also demonstrated. A simple yet effective OD framework for studying bias mitigation is proposed. Using this framework, the performance on popular datasets is analyzed and a significant difference in model performance is observed. Additionally, a knowledge transfer technique and a synthetic image corruption technique are proposed to mitigate the identified bias. Finally, using the DAWN dataset, the findings are validated on the OD task, demonstrating the effectiveness of our techniques in mitigating real-world "good-weather" bias. The experiments show that the proposed techniques outperform baseline methods by averaged fourfold improvement.